{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/video-editing","name":"Video Editing","slug":"video-editing","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Graphs","url":"/area/graphs"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":346,"papers_with_code":133,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":1,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/v2vbench","name":"V2VBench","full_name":"","num_papers_in_archive":2},{"url":"/dataset/five","name":"FiVE","full_name":"A Fine-grained Video Editing Benchmark","num_papers_in_archive":1},{"url":"/dataset/vpbench","name":"VPBench","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vpdata","name":"VPData","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/video-temporal-consistency","name":"Video Temporal Consistency"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":4,"rows_per_page":100,"shown":100,"of":346,"of_with_code":133,"tagged_in_all":346,"counts":{"archive_papers_tagged":346,"with_a_code_link":133,"where_syntology_ran_a_sample":46,"not_listed_spam_title":0,"listed":346,"listed_where_code_ran":46,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":38,"every_run_a_failure_of_syntologys_instrument":8,"listed_with_a_run_with_no_instrument_failure":38,"listed_every_run_a_failure_of_syntologys_instrument":8,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/leo-generative-latent-image-animator-for","slug":"leo-generative-latent-image-animator-for","title":"LEO: Generative Latent Image Animator for Human Video Synthesis","date":"2023-05-06","arxiv_id":"2305.03989","repositories_listed":5,"syntology":null},{"url":"/paper/soccernet-v2-a-dataset-and-benchmarks-for","slug":"soccernet-v2-a-dataset-and-benchmarks-for","title":"SoccerNet-v2: A Dataset and Benchmarks for Holistic Understanding of Broadcast Soccer Videos","date":"2020-11-26","arxiv_id":"2011.13367","repositories_listed":4,"syntology":null},{"url":"/paper/rave-randomized-noise-shuffling-for-fast-and","slug":"rave-randomized-noise-shuffling-for-fast-and","title":"RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models","date":"2023-12-07","arxiv_id":"2312.04524","repositories_listed":3,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rave-randomized-noise-shuffling-for-fast-and#ran","syntology_url":"https://syntology.ai/paper/2312.04524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04524"}},"official":{"repos":["rehg-lab/rave"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/point-to-point-video-generation","slug":"point-to-point-video-generation","title":"Point-to-Point Video Generation","date":"2019-04-05","arxiv_id":"1904.02912","repositories_listed":3,"syntology":null},{"url":"/paper/vace-all-in-one-video-creation-and-editing","slug":"vace-all-in-one-video-creation-and-editing","title":"VACE: All-in-One Video Creation and Editing","date":"2025-03-10","arxiv_id":"2503.07598","repositories_listed":2,"syntology":{"n":19,"n_ran":11,"n_constructed":5,"n_ran_checked":9,"n_instrument":2,"n_unverified":8,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/vace-all-in-one-video-creation-and-editing#ran","syntology_url":"https://syntology.ai/paper/2503.07598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07598"}},"official":null}},{"url":"/paper/re-attentional-controllable-video-diffusion","slug":"re-attentional-controllable-video-diffusion","title":"Re-Attentional Controllable Video Diffusion Editing","date":"2024-12-16","arxiv_id":"2412.11710","repositories_listed":2,"syntology":null},{"url":"/paper/movie-gen-a-cast-of-media-foundation-models","slug":"movie-gen-a-cast-of-media-foundation-models","title":"Movie Gen: A Cast of Media Foundation Models","date":"2024-10-17","arxiv_id":"2410.13720","repositories_listed":2,"syntology":null},{"url":"/paper/e-bench-subjective-aligned-benchmark-suite","slug":"e-bench-subjective-aligned-benchmark-suite","title":"VE-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment","date":"2024-08-21","arxiv_id":"2408.11481","repositories_listed":2,"syntology":null},{"url":"/paper/segment-anything-for-videos-a-systematic","slug":"segment-anything-for-videos-a-systematic","title":"Segment Anything for Videos: A Systematic Survey","date":"2024-07-31","arxiv_id":"2408.08315","repositories_listed":2,"syntology":null},{"url":"/paper/raccoon-remove-add-and-change-video-content","slug":"raccoon-remove-add-and-change-video-content","title":"RACCooN: A Versatile Instructional Video Editing Framework with Auto-Generated Narratives","date":"2024-05-28","arxiv_id":"2405.18406","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/raccoon-remove-add-and-change-video-content#ran","syntology_url":"https://syntology.ai/paper/2405.18406","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18406"}},"official":{"repos":["jaehong31/raccoon"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/moonshot-towards-controllable-video","slug":"moonshot-towards-controllable-video","title":"Moonshot: Towards Controllable Video Generation and Editing with Multimodal Conditions","date":"2024-01-03","arxiv_id":"2401.01827","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/moonshot-towards-controllable-video#ran","syntology_url":"https://syntology.ai/paper/2401.01827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01827"}},"official":{"repos":["salesforce/lavis"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/fdnerf-semantics-driven-face-reconstruction","slug":"fdnerf-semantics-driven-face-reconstruction","title":"FaceDNeRF: Semantics-Driven Face Reconstruction, Prompt Editing and Relighting with Diffusion Models","date":"2023-06-01","arxiv_id":"2306.00783","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fdnerf-semantics-driven-face-reconstruction#ran","syntology_url":"https://syntology.ai/paper/2306.00783","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00783"}},"official":{"repos":["billyxyb/facednerf","billyxyb/fdnerf"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/online-misinformation-video-detection-a","slug":"online-misinformation-video-detection-a","title":"Combating Online Misinformation Videos: Characterization, Detection, and Future Directions","date":"2023-02-07","arxiv_id":"2302.03242","repositories_listed":2,"syntology":null},{"url":"/paper/layered-neural-atlases-for-consistent-video","slug":"layered-neural-atlases-for-consistent-video","title":"Layered Neural Atlases for Consistent Video Editing","date":"2021-09-23","arxiv_id":"2109.11418","repositories_listed":2,"syntology":{"n":17,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":11,"n_pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/layered-neural-atlases-for-consistent-video#ran","syntology_url":"https://syntology.ai/paper/2109.11418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.11418"}},"official":null}},{"url":"/paper/feature-combination-meets-attention-baidu","slug":"feature-combination-meets-attention-baidu","title":"Feature Combination Meets Attention: Baidu Soccer Embeddings and Transformer based Temporal Detection","date":"2021-06-28","arxiv_id":"2106.14447","repositories_listed":2,"syntology":null},{"url":"/paper/non-rigid-neural-radiance-fields","slug":"non-rigid-neural-radiance-fields","title":"Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video","date":"2020-12-22","arxiv_id":"2012.12247","repositories_listed":2,"syntology":null},{"url":"/paper/free-form-video-inpainting-with-3d-gated","slug":"free-form-video-inpainting-with-3d-gated","title":"Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN","date":"2019-04-23","arxiv_id":"1904.10247","repositories_listed":2,"syntology":null},{"url":"/paper/bodynet-volumetric-inference-of-3d-human-body","slug":"bodynet-volumetric-inference-of-3d-human-body","title":"BodyNet: Volumetric Inference of 3D Human Body Shapes","date":"2018-04-13","arxiv_id":"1804.04875","repositories_listed":2,"syntology":null},{"url":"/paper/causally-steered-diffusion-for-automated","slug":"causally-steered-diffusion-for-automated","title":"Causally Steered Diffusion for Automated Video Counterfactual Generation","date":"2025-06-17","arxiv_id":"2506.14404","repositories_listed":1,"syntology":null},{"url":"/paper/fade-frequency-aware-diffusion-model-1","slug":"fade-frequency-aware-diffusion-model-1","title":"FADE: Frequency-Aware Diffusion Model Factorization for Video Editing","date":"2025-06-06","arxiv_id":"2506.05934","repositories_listed":1,"syntology":null},{"url":"/paper/video-editing-for-audio-visual-dubbing","slug":"video-editing-for-audio-visual-dubbing","title":"Video Editing for Audio-Visual Dubbing","date":"2025-05-29","arxiv_id":"2505.23406","repositories_listed":1,"syntology":null},{"url":"/paper/zero-to-hero-zero-shot-initialization","slug":"zero-to-hero-zero-shot-initialization","title":"Zero-to-Hero: Zero-Shot Initialization Empowering Reference-Based Video Appearance Editing","date":"2025-05-29","arxiv_id":"2505.23134","repositories_listed":1,"syntology":null},{"url":"/paper/dc-sam-in-context-segment-anything-in-images","slug":"dc-sam-in-context-segment-anything-in-images","title":"DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency","date":"2025-04-16","arxiv_id":"2504.12080","repositories_listed":1,"syntology":null},{"url":"/paper/flashdepth-real-time-streaming-video-depth","slug":"flashdepth-real-time-streaming-video-depth","title":"FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution","date":"2025-04-09","arxiv_id":"2504.07093","repositories_listed":1,"syntology":null},{"url":"/paper/referdino-plus-2nd-solution-for-4th-pvuw","slug":"referdino-plus-2nd-solution-for-4th-pvuw","title":"ReferDINO-Plus: 2nd Solution for 4th PVUW MeViS Challenge at CVPR 2025","date":"2025-03-30","arxiv_id":"2503.23509","repositories_listed":1,"syntology":null},{"url":"/paper/insvie-1m-effective-instruction-based-video","slug":"insvie-1m-effective-instruction-based-video","title":"InsViE-1M: Effective Instruction-based Video Editing with Elaborate Dataset Construction","date":"2025-03-26","arxiv_id":"2503.20287","repositories_listed":1,"syntology":{"n":18,"n_ran":13,"n_constructed":0,"n_ran_checked":8,"n_instrument":5,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":7,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/insvie-1m-effective-instruction-based-video#ran","syntology_url":"https://syntology.ai/paper/2503.20287","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.20287"}},"official":{"repos":["langmanbusi/insvie"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/wan-open-and-advanced-large-scale-video","slug":"wan-open-and-advanced-large-scale-video","title":"Wan: Open and Advanced Large-Scale Video Generative Models","date":"2025-03-26","arxiv_id":"2503.20314","repositories_listed":1,"syntology":null},{"url":"/paper/alias-free-latent-diffusion-models-improving","slug":"alias-free-latent-diffusion-models-improving","title":"Alias-Free Latent Diffusion Models:Improving Fractional Shift Equivariance of Diffusion Latent Space","date":"2025-03-12","arxiv_id":"2503.09419","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/alias-free-latent-diffusion-models-improving#ran","syntology_url":"https://syntology.ai/paper/2503.09419","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09419"}},"official":{"repos":["singlezombie/afldm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/videopainter-any-length-video-inpainting-and","slug":"videopainter-any-length-video-inpainting-and","title":"VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control","date":"2025-03-07","arxiv_id":"2503.05639","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-temporally-aware-features-for-point","slug":"exploring-temporally-aware-features-for-point","title":"Exploring Temporally-Aware Features for Point Tracking","date":"2025-01-21","arxiv_id":"2501.12218","repositories_listed":1,"syntology":null},{"url":"/paper/sst-em-advanced-metrics-for-evaluating","slug":"sst-em-advanced-metrics-for-evaluating","title":"SST-EM: Advanced Metrics for Evaluating Semantic, Spatial and Temporal Aspects in Video Editing","date":"2025-01-13","arxiv_id":"2501.07554","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-low-cost-video-editing-with","slug":"enhancing-low-cost-video-editing-with","title":"Enhancing Low-Cost Video Editing with Lightweight Adaptors and Temporal-Aware Inversion","date":"2025-01-08","arxiv_id":"2501.04606","repositories_listed":1,"syntology":null},{"url":"/paper/joygen-audio-driven-3d-depth-aware-talking","slug":"joygen-audio-driven-3d-depth-aware-talking","title":"JoyGen: Audio-Driven 3D Depth-Aware Talking-Face Video Editing","date":"2025-01-03","arxiv_id":"2501.01798","repositories_listed":1,"syntology":null},{"url":"/paper/driveeditor-a-unified-3d-information-guided","slug":"driveeditor-a-unified-3d-information-guided","title":"DriveEditor: A Unified 3D Information-Guided Framework for Controllable Object Editing in Driving Scenes","date":"2024-12-27","arxiv_id":"2412.19458","repositories_listed":1,"syntology":null},{"url":"/paper/ditctrl-exploring-attention-control-in-multi","slug":"ditctrl-exploring-attention-control-in-multi","title":"DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation","date":"2024-12-24","arxiv_id":"2412.18597","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ditctrl-exploring-attention-control-in-multi#ran","syntology_url":"https://syntology.ai/paper/2412.18597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.18597"}},"official":{"repos":["tencentarc/ditctrl"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/efficient-neural-network-encoding-for-3d","slug":"efficient-neural-network-encoding-for-3d","title":"Efficient Neural Network Encoding for 3D Color Lookup Tables","date":"2024-12-19","arxiv_id":"2412.15438","repositories_listed":1,"syntology":null},{"url":"/paper/video-seal-open-and-efficient-video","slug":"video-seal-open-and-efficient-video","title":"Video Seal: Open and Efficient Video Watermarking","date":"2024-12-12","arxiv_id":"2412.09492","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/video-seal-open-and-efficient-video#ran","syntology_url":"https://syntology.ai/paper/2412.09492","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09492"}},"official":{"repos":["facebookresearch/videoseal"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/benchmarking-the-robustness-of-optical-flow","slug":"benchmarking-the-robustness-of-optical-flow","title":"Benchmarking the Robustness of Optical Flow Estimation to Corruptions","date":"2024-11-22","arxiv_id":"2411.14865","repositories_listed":1,"syntology":null},{"url":"/paper/stablev2v-stablizing-shape-consistency-in","slug":"stablev2v-stablizing-shape-consistency-in","title":"StableV2V: Stablizing Shape Consistency in Video-to-Video Editing","date":"2024-11-17","arxiv_id":"2411.11045","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/stablev2v-stablizing-shape-consistency-in#ran","syntology_url":"https://syntology.ai/paper/2411.11045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.11045"}},"official":{"repos":["alonzoleeeooo/stablev2v"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/onlyflow-optical-flow-based-motion","slug":"onlyflow-optical-flow-based-motion","title":"OnlyFlow: Optical Flow based Motion Conditioning for Video Diffusion Models","date":"2024-11-15","arxiv_id":"2411.10501","repositories_listed":1,"syntology":null},{"url":"/paper/taming-rectified-flow-for-inversion-and","slug":"taming-rectified-flow-for-inversion-and","title":"Taming Rectified Flow for Inversion and Editing","date":"2024-11-07","arxiv_id":"2411.04746","repositories_listed":1,"syntology":{"n":10,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":10,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/taming-rectified-flow-for-inversion-and#ran","syntology_url":"https://syntology.ai/paper/2411.04746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04746"}},"official":{"repos":["wangjiangshan0725/rf-solver-edit"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/autovfx-physically-realistic-video-editing","slug":"autovfx-physically-realistic-video-editing","title":"AutoVFX: Physically Realistic Video Editing from Natural Language Instructions","date":"2024-11-04","arxiv_id":"2411.02394","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":11,"n_pointer_only":3,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 2 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/autovfx-physically-realistic-video-editing#ran","syntology_url":"https://syntology.ai/paper/2411.02394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02394"}},"official":null}},{"url":"/paper/univst-a-unified-framework-for-training-free","slug":"univst-a-unified-framework-for-training-free","title":"UniVST: A Unified Framework for Training-free Localized Video Style Transfer","date":"2024-10-26","arxiv_id":"2410.20084","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/univst-a-unified-framework-for-training-free#ran","syntology_url":"https://syntology.ai/paper/2410.20084","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20084"}},"official":{"repos":["QuanjianSong/UniVST"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/editboard-towards-a-comprehensive-evaluation","slug":"editboard-towards-a-comprehensive-evaluation","title":"EditBoard: Towards a Comprehensive Evaluation Benchmark for Text-Based Video Editing Models","date":"2024-09-15","arxiv_id":"2409.09668","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/editboard-towards-a-comprehensive-evaluation#ran","syntology_url":"https://syntology.ai/paper/2409.09668","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.09668"}},"official":{"repos":["samchen2003/editboard"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/face-mask-removal-with-region-attentive-face","slug":"face-mask-removal-with-region-attentive-face","title":"Face Mask Removal with Region-attentive Face Inpainting","date":"2024-09-10","arxiv_id":"2409.06845","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-the-training-and-evaluation-of","slug":"rethinking-the-training-and-evaluation-of","title":"Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation","date":"2024-09-07","arxiv_id":"2409.04847","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_honours":2,"n_violates":2,"n_no_contract":4,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 2 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/rethinking-the-training-and-evaluation-of#ran","syntology_url":"https://syntology.ai/paper/2409.04847","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.04847"}},"official":{"repos":["cplusx/rich_context_l2i"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/unveiling-deep-shadows-a-survey-on-image-and","slug":"unveiling-deep-shadows-a-survey-on-image-and","title":"Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Era","date":"2024-09-03","arxiv_id":"2409.02108","repositories_listed":1,"syntology":null},{"url":"/paper/language-driven-interactive-shadow-detection","slug":"language-driven-interactive-shadow-detection","title":"Language-Driven Interactive Shadow Detection","date":"2024-08-16","arxiv_id":"2408.08543","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-the-architecture-design-for","slug":"rethinking-the-architecture-design-for","title":"Rethinking the Architecture Design for Efficient Generic Event Boundary Detection","date":"2024-07-17","arxiv_id":"2407.12622","repositories_listed":1,"syntology":{"n":16,"n_ran":15,"n_constructed":0,"n_ran_checked":11,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":9,"n_pointer_only":16,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/rethinking-the-architecture-design-for#ran","syntology_url":"https://syntology.ai/paper/2407.12622","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.12622"}},"official":{"repos":["ziwei-zheng/efficientgebd"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusion-model-based-video-editing-a-survey","slug":"diffusion-model-based-video-editing-a-survey","title":"Diffusion Model-Based Video Editing: A Survey","date":"2024-06-26","arxiv_id":"2407.07111","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/diffusion-model-based-video-editing-a-survey#ran","syntology_url":"https://syntology.ai/paper/2407.07111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.07111"}},"official":{"repos":["wenhao728/awesome-diffusion-v2v"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mvoc-a-training-free-multiple-video-object","slug":"mvoc-a-training-free-multiple-video-object","title":"MVOC: a training-free multiple video object composition method with diffusion models","date":"2024-06-22","arxiv_id":"2406.15829","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-of-multimodal-guided-image-editing","slug":"a-survey-of-multimodal-guided-image-editing","title":"A Survey of Multimodal-Guided Image Editing with Text-to-Image Diffusion Models","date":"2024-06-20","arxiv_id":"2406.14555","repositories_listed":1,"syntology":null},{"url":"/paper/cove-unleashing-the-diffusion-feature","slug":"cove-unleashing-the-diffusion-feature","title":"COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing","date":"2024-06-13","arxiv_id":"2406.08850","repositories_listed":1,"syntology":null},{"url":"/paper/compositional-video-generation-as-flow","slug":"compositional-video-generation-as-flow","title":"Compositional Video Generation as Flow Equalization","date":"2024-06-10","arxiv_id":"2407.06182","repositories_listed":1,"syntology":null},{"url":"/paper/frag-frequency-adapting-group-for-diffusion","slug":"frag-frequency-adapting-group-for-diffusion","title":"FRAG: Frequency Adapting Group for Diffusion Video Editing","date":"2024-06-10","arxiv_id":"2406.06044","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/frag-frequency-adapting-group-for-diffusion#ran","syntology_url":"https://syntology.ai/paper/2406.06044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06044"}},"official":{"repos":["dbstjswo505/FRAG"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/narcan-natural-refined-canonical-image-with","slug":"narcan-natural-refined-canonical-image-with","title":"NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing","date":"2024-06-10","arxiv_id":"2406.06523","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/narcan-natural-refined-canonical-image-with#ran","syntology_url":"https://syntology.ai/paper/2406.06523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06523"}},"official":{"repos":["koi953215/NaRCan"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/ada-ve-training-free-consistent-video-editing","slug":"ada-ve-training-free-consistent-video-editing","title":"Ada-VE: Training-Free Consistent Video Editing Using Adaptive Motion Prior","date":"2024-06-07","arxiv_id":"2406.04873","repositories_listed":1,"syntology":null},{"url":"/paper/motionfollower-editing-video-motion-via","slug":"motionfollower-editing-video-motion-via","title":"MotionFollower: Editing Video Motion via Lightweight Score-Guided Diffusion","date":"2024-05-30","arxiv_id":"2405.20325","repositories_listed":1,"syntology":null},{"url":"/paper/streaming-video-diffusion-online-video","slug":"streaming-video-diffusion-online-video","title":"Streaming Video Diffusion: Online Video Editing with Diffusion Models","date":"2024-05-30","arxiv_id":"2405.19726","repositories_listed":1,"syntology":null},{"url":"/paper/slicedit-zero-shot-video-editing-with-text-to","slug":"slicedit-zero-shot-video-editing-with-text-to","title":"Slicedit: Zero-Shot Video Editing With Text-to-Image Diffusion Models Using Spatio-Temporal Slices","date":"2024-05-20","arxiv_id":"2405.12211","repositories_listed":1,"syntology":{"n":20,"n_ran":9,"n_constructed":0,"n_ran_checked":3,"n_instrument":6,"n_unverified":11,"n_honours":2,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/slicedit-zero-shot-video-editing-with-text-to#ran","syntology_url":"https://syntology.ai/paper/2405.12211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.12211"}},"official":{"repos":["fallenshock/Slicedit"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/v2a-mark-versatile-deep-visual-audio","slug":"v2a-mark-versatile-deep-visual-audio","title":"V2A-Mark: Versatile Deep Visual-Audio Watermarking for Manipulation Localization and Copyright Protection","date":"2024-04-25","arxiv_id":"2404.16824","repositories_listed":1,"syntology":null},{"url":"/paper/anyv2v-a-plug-and-play-framework-for-any","slug":"anyv2v-a-plug-and-play-framework-for-any","title":"AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks","date":"2024-03-21","arxiv_id":"2403.14468","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/anyv2v-a-plug-and-play-framework-for-any#ran","syntology_url":"https://syntology.ai/paper/2403.14468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14468"}},"official":{"repos":["tiger-ai-lab/anyv2v"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/mora-enabling-generalist-video-generation-via","slug":"mora-enabling-generalist-video-generation-via","title":"Mora: Enabling Generalist Video Generation via A Multi-Agent Framework","date":"2024-03-20","arxiv_id":"2403.13248","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mora-enabling-generalist-video-generation-via#ran","syntology_url":"https://syntology.ai/paper/2403.13248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13248"}},"official":{"repos":["lichao-sun/mora"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/echoreel-enhancing-action-generation-of","slug":"echoreel-enhancing-action-generation-of","title":"AICL: Action In-Context Learning for Video Diffusion Model","date":"2024-03-18","arxiv_id":"2403.11535","repositories_listed":1,"syntology":null},{"url":"/paper/effived-efficient-video-editing-via-text","slug":"effived-efficient-video-editing-via-text","title":"EffiVED:Efficient Video Editing via Text-instruction Diffusion Models","date":"2024-03-18","arxiv_id":"2403.11568","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-contextualized-diffusion-models","slug":"cross-modal-contextualized-diffusion-models","title":"Contextualized Diffusion Models for Text-Guided Image and Video Generation","date":"2024-02-26","arxiv_id":"2402.16627","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cross-modal-contextualized-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2402.16627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16627"}},"official":{"repos":["yangling0818/contextdiff"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lumiere-a-space-time-diffusion-model-for","slug":"lumiere-a-space-time-diffusion-model-for","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","date":"2024-01-23","arxiv_id":"2401.12945","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lumiere-a-space-time-diffusion-model-for#ran","syntology_url":"https://syntology.ai/paper/2401.12945","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12945"}},"official":null}},{"url":"/paper/fed-nerf-achieve-high-3d-consistency-and","slug":"fed-nerf-achieve-high-3d-consistency-and","title":"FED-NeRF: Achieve High 3D Consistency and Temporal Coherence for Face Video Editing on Dynamic NeRF","date":"2024-01-05","arxiv_id":"2401.02616","repositories_listed":1,"syntology":null},{"url":"/paper/implicit-motion-function","slug":"implicit-motion-function","title":"Implicit Motion Function","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/vidtome-video-token-merging-for-zero-shot","slug":"vidtome-video-token-merging-for-zero-shot","title":"VidToMe: Video Token Merging for Zero-Shot Video Editing","date":"2023-12-17","arxiv_id":"2312.10656","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":7,"n_instrument":5,"n_unverified":4,"n_honours":2,"n_violates":2,"n_no_contract":3,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 2 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/vidtome-video-token-merging-for-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2312.10656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10656"}},"official":{"repos":["lixirui142/VidToMe"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/a-video-is-worth-256-bases-spatial-temporal","slug":"a-video-is-worth-256-bases-spatial-temporal","title":"A Video is Worth 256 Bases: Spatial-Temporal Expectation-Maximization Inversion for Zero-Shot Video Editing","date":"2023-12-10","arxiv_id":"2312.05856","repositories_listed":1,"syntology":null},{"url":"/paper/motioncrafter-one-shot-motion-customization","slug":"motioncrafter-one-shot-motion-customization","title":"MotionCrafter: One-Shot Motion Customization of Diffusion Models","date":"2023-12-08","arxiv_id":"2312.05288","repositories_listed":1,"syntology":null},{"url":"/paper/bivdiff-a-training-free-framework-for-general","slug":"bivdiff-a-training-free-framework-for-general","title":"BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models","date":"2023-12-05","arxiv_id":"2312.02813","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/bivdiff-a-training-free-framework-for-general#ran","syntology_url":"https://syntology.ai/paper/2312.02813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02813"}},"official":{"repos":["mcg-nju/bivdiff"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/magicstick-controllable-video-editing-via","slug":"magicstick-controllable-video-editing-via","title":"MagicStick: Controllable Video Editing via Control Handle Transformations","date":"2023-12-05","arxiv_id":"2312.03047","repositories_listed":1,"syntology":null},{"url":"/paper/dragvideo-interactive-drag-style-video","slug":"dragvideo-interactive-drag-style-video","title":"DragVideo: Interactive Drag-style Video Editing","date":"2023-12-03","arxiv_id":"2312.02216","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":14,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dragvideo-interactive-drag-style-video#ran","syntology_url":"https://syntology.ai/paper/2312.02216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02216"}},"official":{"repos":["rickyskywalker/dragvideo-official"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/vmc-video-motion-customization-using-temporal","slug":"vmc-video-motion-customization-using-temporal","title":"VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models","date":"2023-12-01","arxiv_id":"2312.00845","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vmc-video-motion-customization-using-temporal#ran","syntology_url":"https://syntology.ai/paper/2312.00845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00845"}},"official":{"repos":["HyeonHo99/Video-Motion-Customization"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/motioneditor-editing-video-motion-via-content","slug":"motioneditor-editing-video-motion-via-content","title":"MotionEditor: Editing Video Motion via Content-Aware Diffusion","date":"2023-11-30","arxiv_id":"2311.18830","repositories_listed":1,"syntology":null},{"url":"/paper/videoassembler-identity-consistent-video","slug":"videoassembler-identity-consistent-video","title":"MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing","date":"2023-11-29","arxiv_id":"2311.17338","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":2,"n_no_contract":7,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 2 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/videoassembler-identity-consistent-video#ran","syntology_url":"https://syntology.ai/paper/2311.17338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17338"}},"official":{"repos":["gulucaptain/videoassembler"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sketch-video-synthesis","slug":"sketch-video-synthesis","title":"Sketch Video Synthesis","date":"2023-11-26","arxiv_id":"2311.15306","repositories_listed":1,"syntology":null},{"url":"/paper/clearer-frames-anytime-resolving-velocity","slug":"clearer-frames-anytime-resolving-velocity","title":"Clearer Frames, Anytime: Resolving Velocity Ambiguity in Video Frame Interpolation","date":"2023-11-14","arxiv_id":"2311.08007","repositories_listed":1,"syntology":null},{"url":"/paper/consistent-video-to-video-transfer-using","slug":"consistent-video-to-video-transfer-using","title":"Consistent Video-to-Video Transfer Using Synthetic Dataset","date":"2023-11-01","arxiv_id":"2311.00213","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":2,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/consistent-video-to-video-transfer-using#ran","syntology_url":"https://syntology.ai/paper/2311.00213","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.00213"}},"official":{"repos":["amazon-science/instruct-video-to-video"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/fuse-your-latents-video-editing-with-multi","slug":"fuse-your-latents-video-editing-with-multi","title":"Fuse Your Latents: Video Editing with Multi-source Latent Diffusion Models","date":"2023-10-25","arxiv_id":"2310.16400","repositories_listed":1,"syntology":null},{"url":"/paper/cvpr-2023-text-guided-video-editing","slug":"cvpr-2023-text-guided-video-editing","title":"CVPR 2023 Text Guided Video Editing Competition","date":"2023-10-24","arxiv_id":"2310.16003","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/cvpr-2023-text-guided-video-editing#ran","syntology_url":"https://syntology.ai/paper/2310.16003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16003"}},"official":{"repos":["showlab/loveu-tgve-2023"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/a-survey-on-video-diffusion-models","slug":"a-survey-on-video-diffusion-models","title":"A Survey on Video Diffusion Models","date":"2023-10-16","arxiv_id":"2310.10647","repositories_listed":1,"syntology":null},{"url":"/paper/lamp-learn-a-motion-pattern-for-few-shot","slug":"lamp-learn-a-motion-pattern-for-few-shot","title":"LAMP: Learn A Motion Pattern for Few-Shot-Based Video Generation","date":"2023-10-16","arxiv_id":"2310.10769","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lamp-learn-a-motion-pattern-for-few-shot#ran","syntology_url":"https://syntology.ai/paper/2310.10769","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10769"}},"official":{"repos":["RQ-Wu/LAMP"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lovecon-text-driven-training-free-long-video","slug":"lovecon-text-driven-training-free-long-video","title":"LOVECon: Text-driven Training-Free Long Video Editing with ControlNet","date":"2023-10-15","arxiv_id":"2310.09711","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-cognitive-consensus-guided-audio","slug":"cross-modal-cognitive-consensus-guided-audio","title":"Cross-modal Cognitive Consensus guided Audio-Visual Segmentation","date":"2023-10-10","arxiv_id":"2310.06259","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/cross-modal-cognitive-consensus-guided-audio#ran","syntology_url":"https://syntology.ai/paper/2310.06259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06259"}},"official":{"repos":["zhaofengshi/avs-c3n"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/flatten-optical-flow-guided-attention-for","slug":"flatten-optical-flow-guided-attention-for","title":"FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing","date":"2023-10-09","arxiv_id":"2310.05922","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/flatten-optical-flow-guided-attention-for#ran","syntology_url":"https://syntology.ai/paper/2310.05922","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05922"}},"official":null}},{"url":"/paper/ground-a-video-zero-shot-grounded-video","slug":"ground-a-video-zero-shot-grounded-video","title":"Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models","date":"2023-10-02","arxiv_id":"2310.01107","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":12,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/ground-a-video-zero-shot-grounded-video#ran","syntology_url":"https://syntology.ai/paper/2310.01107","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.01107"}},"official":{"repos":["ground-a-video/ground-a-video"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/ccedit-creative-and-controllable-video","slug":"ccedit-creative-and-controllable-video","title":"CCEdit: Creative and Controllable Video Editing via Diffusion Models","date":"2023-09-28","arxiv_id":"2309.16496","repositories_listed":1,"syntology":null},{"url":"/paper/1st-place-solution-for-the-5th-lsvos","slug":"1st-place-solution-for-the-5th-lsvos","title":"1st Place Solution for the 5th LSVOS Challenge: Video Instance Segmentation","date":"2023-08-28","arxiv_id":"2308.14392","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-3d-gaussians-tracking-by-persistent","slug":"dynamic-3d-gaussians-tracking-by-persistent","title":"Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis","date":"2023-08-18","arxiv_id":"2308.09713","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dynamic-3d-gaussians-tracking-by-persistent#ran","syntology_url":"https://syntology.ai/paper/2308.09713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09713"}},"official":{"repos":["JonathonLuiten/Dynamic3DGaussians"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/stablevideo-text-driven-consistency-aware","slug":"stablevideo-text-driven-consistency-aware","title":"StableVideo: Text-driven Consistency-aware Diffusion Video Editing","date":"2023-08-18","arxiv_id":"2308.09592","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":2,"n_no_contract":2,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/stablevideo-text-driven-consistency-aware#ran","syntology_url":"https://syntology.ai/paper/2308.09592","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09592"}},"official":{"repos":["rese1f/stablevideo"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/edit-temporal-consistent-videos-with-image","slug":"edit-temporal-consistent-videos-with-image","title":"Edit Temporal-Consistent Videos with Image Diffusion Model","date":"2023-08-17","arxiv_id":"2308.09091","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/edit-temporal-consistent-videos-with-image#ran","syntology_url":"https://syntology.ai/paper/2308.09091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09091"}},"official":{"repos":["mdswyz/TCVE"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/tokenflow-consistent-diffusion-features-for","slug":"tokenflow-consistent-diffusion-features-for","title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","date":"2023-07-19","arxiv_id":"2307.10373","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":3,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tokenflow-consistent-diffusion-features-for#ran","syntology_url":"https://syntology.ai/paper/2307.10373","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.10373"}},"official":null}},{"url":"/paper/1st-place-solution-for-pvuw-challenge-2023","slug":"1st-place-solution-for-pvuw-challenge-2023","title":"1st Place Solution for PVUW Challenge 2023: Video Panoptic Segmentation","date":"2023-06-07","arxiv_id":"2306.04091","repositories_listed":1,"syntology":null},{"url":"/paper/dvis-decoupled-video-instance-segmentation","slug":"dvis-decoupled-video-instance-segmentation","title":"DVIS: Decoupled Video Instance Segmentation Framework","date":"2023-06-06","arxiv_id":"2306.03413","repositories_listed":1,"syntology":null},{"url":"/paper/dugmatting-decomposed-uncertainty-guided","slug":"dugmatting-decomposed-uncertainty-guided","title":"dugMatting: Decomposed-Uncertainty-Guided Matting","date":"2023-06-02","arxiv_id":"2306.01452","repositories_listed":1,"syntology":{"n":10,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/dugmatting-decomposed-uncertainty-guided#ran","syntology_url":"https://syntology.ai/paper/2306.01452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.01452"}},"official":{"repos":["fire-friend/dugmatting"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/save-spectral-shift-aware-adaptation-of-image","slug":"save-spectral-shift-aware-adaptation-of-image","title":"SAVE: Spectral-Shift-Aware Adaptation of Image Diffusion Models for Text-driven Video Editing","date":"2023-05-30","arxiv_id":"2305.18670","repositories_listed":1,"syntology":null},{"url":"/paper/controlvideo-adding-conditional-control-for","slug":"controlvideo-adding-conditional-control-for","title":"ControlVideo: Conditional Control for One-shot Text-driven Video Editing and Beyond","date":"2023-05-26","arxiv_id":"2305.17098","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/controlvideo-adding-conditional-control-for#ran","syntology_url":"https://syntology.ai/paper/2305.17098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17098"}},"official":{"repos":["thu-ml/controlvideo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}}],"syntology_records":42,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":46,"papers_where_code_ran_first_page":"/task/video-editing/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":4,"url":"/task/video-editing/papers/2","json":"/task/video-editing/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/video-editing/papers/3","json":"/task/video-editing/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/video-editing/papers/4","json":"/task/video-editing/papers/4.json","rows":46},{"order":"ran","page":1,"of":1,"url":"/task/video-editing/papers/ran/1","json":"/task/video-editing/papers/ran/1.json","rows":46}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"4d85a3e5ac275fe5c008c3c9493d240dfb89d573e5d41829dba393f32dc67c21","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}