{"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/3d-visual-grounding","name":"3D visual grounding","slug":"3d-visual-grounding","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":82,"papers_with_code":39,"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":2,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[{"url":"/dataset/mono3drefer","name":"Mono3DRefer","full_name":"","num_papers_in_archive":3},{"url":"/dataset/beacon3d","name":"Beacon3D","full_name":"","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[{"url":"/task/visual-grounding","name":"Visual Grounding"}],"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":1,"rows_per_page":100,"shown":82,"of":82,"of_with_code":39,"tagged_in_all":82,"counts":{"archive_papers_tagged":82,"with_a_code_link":39,"where_syntology_ran_a_sample":19,"not_listed_spam_title":0,"listed":82,"listed_where_code_ran":19,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":17,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":17,"listed_every_run_a_failure_of_syntologys_instrument":2,"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/viewrefer-grasp-the-multi-view-knowledge-for","slug":"viewrefer-grasp-the-multi-view-knowledge-for","title":"ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance","date":"2023-03-29","arxiv_id":"2303.16894","repositories_listed":7,"syntology":{"n":12,"n_ran":8,"n_constructed":2,"n_ran_checked":6,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":12,"phrase":"8 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/viewrefer-grasp-the-multi-view-knowledge-for#ran","syntology_url":"https://syntology.ai/paper/2303.16894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16894"}},"official":{"repos":["ivan-tang-3d/viewrefer3d","ziyuguo99/viewrefer3d"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/eda-explicit-text-decoupling-and-dense","slug":"eda-explicit-text-decoupling-and-dense","title":"EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding","date":"2022-09-29","arxiv_id":"2209.14941","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/eda-explicit-text-decoupling-and-dense#ran","syntology_url":"https://syntology.ai/paper/2209.14941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.14941"}},"official":{"repos":["yanmin-wu/eda"],"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/refer-it-in-rgbd-a-bottom-up-approach-for-3d","slug":"refer-it-in-rgbd-a-bottom-up-approach-for-3d","title":"Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images","date":"2021-03-14","arxiv_id":"2103.07894","repositories_listed":2,"syntology":{"n":16,"n_ran":11,"n_constructed":10,"n_ran_checked":10,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":6,"phrase":"11 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/refer-it-in-rgbd-a-bottom-up-approach-for-3d#ran","syntology_url":"https://syntology.ai/paper/2103.07894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.07894"}},"official":null}},{"url":"/paper/extending-large-vision-language-model-for","slug":"extending-large-vision-language-model-for","title":"Extending Large Vision-Language Model for Diverse Interactive Tasks in Autonomous Driving","date":"2025-05-13","arxiv_id":"2505.08725","repositories_listed":1,"syntology":null},{"url":"/paper/as3d-2d-assisted-cross-modal-understanding","slug":"as3d-2d-assisted-cross-modal-understanding","title":"AS3D: 2D-Assisted Cross-Modal Understanding with Semantic-Spatial Scene Graphs for 3D Visual Grounding","date":"2025-05-07","arxiv_id":"2505.04058","repositories_listed":1,"syntology":null},{"url":"/paper/ges3vig-incorporating-pointing-gestures-into","slug":"ges3vig-incorporating-pointing-gestures-into","title":"Ges3ViG: Incorporating Pointing Gestures into Language-Based 3D Visual Grounding for Embodied Reference Understanding","date":"2025-04-13","arxiv_id":"2504.09623","repositories_listed":1,"syntology":null},{"url":"/paper/unveiling-the-mist-over-3d-vision-language","slug":"unveiling-the-mist-over-3d-vision-language","title":"Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis","date":"2025-03-28","arxiv_id":"2503.22420","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 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; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unveiling-the-mist-over-3d-vision-language#ran","syntology_url":"https://syntology.ai/paper/2503.22420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.22420"}},"official":{"repos":["beacon-3d/beacon-3d"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/text-guided-sparse-voxel-pruning-for","slug":"text-guided-sparse-voxel-pruning-for","title":"Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding","date":"2025-02-14","arxiv_id":"2502.10392","repositories_listed":1,"syntology":null},{"url":"/paper/evolving-symbolic-3d-visual-grounder-with","slug":"evolving-symbolic-3d-visual-grounder-with","title":"Evolving Symbolic 3D Visual Grounder with Weakly Supervised Reflection","date":"2025-02-03","arxiv_id":"2502.01401","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/evolving-symbolic-3d-visual-grounder-with#ran","syntology_url":"https://syntology.ai/paper/2502.01401","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.01401"}},"official":{"repos":["openrobotlab/ease"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/ges3vig-incorporating-pointing-gestures-into-1","slug":"ges3vig-incorporating-pointing-gestures-into-1","title":"Ges3ViG : Incorporating Pointing Gestures into Language-Based 3D Visual Grounding for Embodied Reference Understanding","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/bip3d-bridging-2d-images-and-3d-perception","slug":"bip3d-bridging-2d-images-and-3d-perception","title":"BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligence","date":"2024-11-22","arxiv_id":"2411.14869","repositories_listed":1,"syntology":null},{"url":"/paper/solving-zero-shot-3d-visual-grounding-as","slug":"solving-zero-shot-3d-visual-grounding-as","title":"Solving Zero-Shot 3D Visual Grounding as Constraint Satisfaction Problems","date":"2024-11-21","arxiv_id":"2411.14594","repositories_listed":1,"syntology":null},{"url":"/paper/vlm-grounder-a-vlm-agent-for-zero-shot-3d","slug":"vlm-grounder-a-vlm-agent-for-zero-shot-3d","title":"VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding","date":"2024-10-17","arxiv_id":"2410.13860","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":0,"n_no_contract":4,"n_pointer_only":11,"phrase":"10 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vlm-grounder-a-vlm-agent-for-zero-shot-3d#ran","syntology_url":"https://syntology.ai/paper/2410.13860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13860"}},"official":{"repos":["openrobotlab/vlm-grounder"],"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/refmask3d-language-guided-transformer-for-3d","slug":"refmask3d-language-guided-transformer-for-3d","title":"RefMask3D: Language-Guided Transformer for 3D Referring Segmentation","date":"2024-07-25","arxiv_id":"2407.18244","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":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) · 0 unverified","sample_list":"/paper/refmask3d-language-guided-transformer-for-3d#ran","syntology_url":"https://syntology.ai/paper/2407.18244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.18244"}},"official":{"repos":["heshuting555/refmask3d"],"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/multi-branch-collaborative-learning-network","slug":"multi-branch-collaborative-learning-network","title":"Multi-branch Collaborative Learning Network for 3D Visual Grounding","date":"2024-07-07","arxiv_id":"2407.05363","repositories_listed":1,"syntology":null},{"url":"/paper/mmscan-a-multi-modal-3d-scene-dataset-with","slug":"mmscan-a-multi-modal-3d-scene-dataset-with","title":"MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations","date":"2024-06-13","arxiv_id":"2406.09401","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-text-guided-3d-visual-grounding","slug":"a-survey-on-text-guided-3d-visual-grounding","title":"A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions","date":"2024-06-09","arxiv_id":"2406.05785","repositories_listed":1,"syntology":null},{"url":"/paper/talk2radar-bridging-natural-language-with-4d","slug":"talk2radar-bridging-natural-language-with-4d","title":"Talk2Radar: Bridging Natural Language with 4D mmWave Radar for 3D Referring Expression Comprehension","date":"2024-05-21","arxiv_id":"2405.12821","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-3d-dense-caption-and-visual","slug":"rethinking-3d-dense-caption-and-visual","title":"Rethinking 3D Dense Caption and Visual Grounding in A Unified Framework through Prompt-based Localization","date":"2024-04-17","arxiv_id":"2404.11064","repositories_listed":1,"syntology":null},{"url":"/paper/secg-semantic-enhanced-3d-visual-grounding","slug":"secg-semantic-enhanced-3d-visual-grounding","title":"SeCG: Semantic-Enhanced 3D Visual Grounding via Cross-modal Graph Attention","date":"2024-03-13","arxiv_id":"2403.08182","repositories_listed":1,"syntology":null},{"url":"/paper/mikasa-multi-key-anchor-scene-aware","slug":"mikasa-multi-key-anchor-scene-aware","title":"MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding","date":"2024-03-05","arxiv_id":"2403.03077","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":10,"n_ran_checked":11,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":16,"phrase":"11 ran (of which 10 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/mikasa-multi-key-anchor-scene-aware#ran","syntology_url":"https://syntology.ai/paper/2403.03077","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.03077"}},"official":{"repos":["dfki-av/mikasa-3dvg"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":10,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-attribute-interactions-matter-for-3d","slug":"multi-attribute-interactions-matter-for-3d","title":"Multi-Attribute Interactions Matter for 3D Visual Grounding","date":"2024-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mono3dvg-3d-visual-grounding-in-monocular","slug":"mono3dvg-3d-visual-grounding-in-monocular","title":"Mono3DVG: 3D Visual Grounding in Monocular Images","date":"2023-12-13","arxiv_id":"2312.08022","repositories_listed":1,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"6 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/mono3dvg-3d-visual-grounding-in-monocular#ran","syntology_url":"https://syntology.ai/paper/2312.08022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.08022"}},"official":{"repos":["zhanyang-nwpu/mono3dvg"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/visual-programming-for-zero-shot-open","slug":"visual-programming-for-zero-shot-open","title":"Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding","date":"2023-11-26","arxiv_id":"2311.15383","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visual-programming-for-zero-shot-open#ran","syntology_url":"https://syntology.ai/paper/2311.15383","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15383"}},"official":{"repos":["CurryYuan/ZSVG3D"],"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/cityrefer-geography-aware-3d-visual-grounding","slug":"cityrefer-geography-aware-3d-visual-grounding","title":"CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data","date":"2023-10-28","arxiv_id":"2310.18773","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cityrefer-geography-aware-3d-visual-grounding#ran","syntology_url":"https://syntology.ai/paper/2310.18773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.18773"}},"official":{"repos":["atr-dbi/cityrefer"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/cot3dref-chain-of-thoughts-data-efficient-3d","slug":"cot3dref-chain-of-thoughts-data-efficient-3d","title":"CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding","date":"2023-10-10","arxiv_id":"2310.06214","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cot3dref-chain-of-thoughts-data-efficient-3d#ran","syntology_url":"https://syntology.ai/paper/2310.06214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.06214"}},"official":{"repos":["eslambakr/CoT3D_VG"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/llm-grounder-open-vocabulary-3d-visual","slug":"llm-grounder-open-vocabulary-3d-visual","title":"LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent","date":"2023-09-21","arxiv_id":"2309.12311","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"5 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/llm-grounder-open-vocabulary-3d-visual#ran","syntology_url":"https://syntology.ai/paper/2309.12311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.12311"}},"official":{"repos":["sled-group/chat-with-nerf"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/multi3drefer-grounding-text-description-to","slug":"multi3drefer-grounding-text-description-to","title":"Multi3DRefer: Grounding Text Description to Multiple 3D Objects","date":"2023-09-11","arxiv_id":"2309.05251","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/multi3drefer-grounding-text-description-to#ran","syntology_url":"https://syntology.ai/paper/2309.05251","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05251"}},"official":{"repos":["3dlg-hcvc/M3DRef-CLIP"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/distilling-coarse-to-fine-semantic-matching","slug":"distilling-coarse-to-fine-semantic-matching","title":"Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly Supervised 3D Visual Grounding","date":"2023-07-18","arxiv_id":"2307.09267","repositories_listed":1,"syntology":null},{"url":"/paper/cross3dvg-baseline-and-dataset-for-cross","slug":"cross3dvg-baseline-and-dataset-for-cross","title":"Cross3DVG: Cross-Dataset 3D Visual Grounding on Different RGB-D Scans","date":"2023-05-23","arxiv_id":"2305.13876","repositories_listed":1,"syntology":null},{"url":"/paper/wildrefer-3d-object-localization-in-large","slug":"wildrefer-3d-object-localization-in-large","title":"WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural Language","date":"2023-04-12","arxiv_id":"2304.05645","repositories_listed":1,"syntology":null},{"url":"/paper/scaneru-interactive-3d-visual-grounding-based","slug":"scaneru-interactive-3d-visual-grounding-based","title":"ScanERU: Interactive 3D Visual Grounding based on Embodied Reference Understanding","date":"2023-03-23","arxiv_id":"2303.13186","repositories_listed":1,"syntology":null},{"url":"/paper/context-aware-alignment-and-mutual-masking","slug":"context-aware-alignment-and-mutual-masking","title":"Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/look-around-and-refer-2d-synthetic-semantics","slug":"look-around-and-refer-2d-synthetic-semantics","title":"Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual Grounding","date":"2022-11-25","arxiv_id":"2211.14241","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":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) · 1 unverified","sample_list":"/paper/look-around-and-refer-2d-synthetic-semantics#ran","syntology_url":"https://syntology.ai/paper/2211.14241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.14241"}},"official":{"repos":["eslambakr/LAR-Look-Around-and-Refer"],"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/ham-hierarchical-attention-model-with-high","slug":"ham-hierarchical-attention-model-with-high","title":"Learning Point-Language Hierarchical Alignment for 3D Visual Grounding","date":"2022-10-22","arxiv_id":"2210.12513","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/ham-hierarchical-attention-model-with-high#ran","syntology_url":"https://syntology.ai/paper/2210.12513","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12513"}},"official":{"repos":["ppjmchen/ham"],"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/3d-sps-single-stage-3d-visual-grounding-via","slug":"3d-sps-single-stage-3d-visual-grounding-via","title":"3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection","date":"2022-04-13","arxiv_id":"2204.06272","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/3d-sps-single-stage-3d-visual-grounding-via#ran","syntology_url":"https://syntology.ai/paper/2204.06272","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.06272"}},"official":{"repos":["fjhzhixi/3d-sps"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-view-transformer-for-3d-visual","slug":"multi-view-transformer-for-3d-visual","title":"Multi-View Transformer for 3D Visual Grounding","date":"2022-04-05","arxiv_id":"2204.02174","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":1,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":4,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-view-transformer-for-3d-visual#ran","syntology_url":"https://syntology.ai/paper/2204.02174","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.02174"}},"official":{"repos":["sega-hsj/mvt-3dvg"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sat-2d-semantics-assisted-training-for-3d","slug":"sat-2d-semantics-assisted-training-for-3d","title":"SAT: 2D Semantics Assisted Training for 3D Visual Grounding","date":"2021-05-24","arxiv_id":"2105.11450","repositories_listed":1,"syntology":null},{"url":"/paper/instancerefer-cooperative-holistic","slug":"instancerefer-cooperative-holistic","title":"InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring","date":"2021-03-01","arxiv_id":"2103.01128","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/instancerefer-cooperative-holistic#ran","syntology_url":"https://syntology.ai/paper/2103.01128","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.01128"}},"official":{"repos":["CurryYuan/InstanceRefer"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":null,"slug":"viewsrd-3d-visual-grounding-via-structured","title":"ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition","date":"2025-07-15","arxiv_id":"2507.11261","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-neural-representation-framework-with-llm","title":"A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual Grounding","date":"2025-07-09","arxiv_id":"2507.06719","repositories_listed":0,"syntology":null},{"url":null,"slug":"spazer-spatial-semantic-progressive-reasoning","title":"SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding","date":"2025-06-27","arxiv_id":"2506.21924","repositories_listed":0,"syntology":null},{"url":null,"slug":"groundflow-a-plug-in-module-for-temporal","title":"GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding","date":"2025-06-26","arxiv_id":"2506.21188","repositories_listed":0,"syntology":null},{"url":null,"slug":"i-speak-and-you-find-robust-3d-visual","title":"I Speak and You Find: Robust 3D Visual Grounding with Noisy and Ambiguous Speech Inputs","date":"2025-06-17","arxiv_id":"2506.14495","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-representation-space-for-3d-visual","title":"Unified Representation Space for 3D Visual Grounding","date":"2025-06-17","arxiv_id":"2506.14238","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-objects-to-anywhere-a-holistic-benchmark","title":"From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes","date":"2025-06-05","arxiv_id":"2506.04897","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-3d-visual-grounding-from-vision","title":"Zero-Shot 3D Visual Grounding from Vision-Language Models","date":"2025-05-28","arxiv_id":"2505.22429","repositories_listed":0,"syntology":null},{"url":null,"slug":"densegrounding-improving-dense-language","title":"DenseGrounding: Improving Dense Language-Vision Semantics for Ego-Centric 3D Visual Grounding","date":"2025-05-08","arxiv_id":"2505.04965","repositories_listed":0,"syntology":null},{"url":null,"slug":"dsm-building-a-diverse-semantic-map-for-3d","title":"DSM: Building A Diverse Semantic Map for 3D Visual Grounding","date":"2025-04-11","arxiv_id":"2504.08307","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasongrounder-lvlm-guided-hierarchical","title":"ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning","date":"2025-03-30","arxiv_id":"2503.23297","repositories_listed":0,"syntology":null},{"url":null,"slug":"nugrounding-a-multi-view-3d-visual-grounding","title":"NuGrounding: A Multi-View 3D Visual Grounding Framework in Autonomous Driving","date":"2025-03-28","arxiv_id":"2503.22436","repositories_listed":0,"syntology":null},{"url":null,"slug":"proxytransformation-preshaping-point-cloud","title":"ProxyTransformation: Preshaping Point Cloud Manifold With Proxy Attention For 3D Visual Grounding","date":"2025-02-26","arxiv_id":"2502.19247","repositories_listed":0,"syntology":null},{"url":null,"slug":"augrefer-advancing-3d-visual-grounding-via","title":"AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring","date":"2025-01-16","arxiv_id":"2501.09428","repositories_listed":0,"syntology":null},{"url":null,"slug":"vigil3d-a-linguistically-diverse-dataset-for","title":"ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding","date":"2025-01-02","arxiv_id":"2501.01366","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-human-perception-understanding-multi","title":"Beyond Human Perception: Understanding Multi-Object World from Monocular View","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-spatial-understanding-in-mllms","title":"3D Spatial Understanding in MLLMs: Disambiguation and Evaluation","date":"2024-12-09","arxiv_id":"2412.06613","repositories_listed":0,"syntology":null},{"url":null,"slug":"seeground-see-and-ground-for-zero-shot-open","title":"SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding","date":"2024-12-05","arxiv_id":"2412.04383","repositories_listed":0,"syntology":null},{"url":null,"slug":"3d-scene-graph-guided-vision-language-pre","title":"3D Scene Graph Guided Vision-Language Pre-training","date":"2024-11-27","arxiv_id":"2411.18666","repositories_listed":0,"syntology":null},{"url":null,"slug":"lidarefer-outdoor-3d-visual-grounding-for","title":"LidaRefer: Outdoor 3D Visual Grounding for Autonomous Driving with Transformers","date":"2024-11-07","arxiv_id":"2411.04351","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-grained-spatial-and-verbal-losses-for-3d","title":"Fine-Grained Spatial and Verbal Losses for 3D Visual Grounding","date":"2024-11-05","arxiv_id":"2411.03405","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-top-down-and-bottom-up-frameworks-for","title":"Joint Top-Down and Bottom-Up Frameworks for 3D Visual Grounding","date":"2024-10-21","arxiv_id":"2410.15615","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-self-training-for-semi-supervised-3d","title":"Bayesian Self-Training for Semi-Supervised 3D Segmentation","date":"2024-09-12","arxiv_id":"2409.08102","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-oriented-sequential-grounding-in-3d","title":"Task-oriented Sequential Grounding in 3D Scenes","date":"2024-08-07","arxiv_id":"2408.04034","repositories_listed":0,"syntology":null},{"url":null,"slug":"pd-tpe-parallel-decoder-with-text-guided","title":"PD-APE: A Parallel Decoding Framework with Adaptive Position Encoding for 3D Visual Grounding","date":"2024-07-19","arxiv_id":"2407.14491","repositories_listed":0,"syntology":null},{"url":null,"slug":"empowering-3d-visual-grounding-with-reasoning","title":"ScanReason: Empowering 3D Visual Grounding with Reasoning Capabilities","date":"2024-07-01","arxiv_id":"2407.01525","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-attribute-spatial-relation-alignment-for","title":"Dual Attribute-Spatial Relation Alignment for 3D Visual Grounding","date":"2024-06-13","arxiv_id":"2406.08907","repositories_listed":0,"syntology":null},{"url":null,"slug":"intent3d-3d-object-detection-in-rgb-d-scans","title":"Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention","date":"2024-05-28","arxiv_id":"2405.18295","repositories_listed":0,"syntology":null},{"url":null,"slug":"talk-to-parallel-lidars-a-human-lidar","title":"Talk to Parallel LiDARs: A Human-LiDAR Interaction Method Based on 3D Visual Grounding","date":"2024-05-24","arxiv_id":"2405.15274","repositories_listed":0,"syntology":null},{"url":null,"slug":"naturally-supervised-3d-visual-grounding-with","title":"Naturally Supervised 3D Visual Grounding with Language-Regularized Concept Learners","date":"2024-04-30","arxiv_id":"2404.19696","repositories_listed":0,"syntology":null},{"url":null,"slug":"dora-3d-visual-grounding-with-order-aware","title":"Data-Efficient 3D Visual Grounding via Order-Aware Referring","date":"2024-03-25","arxiv_id":"2403.16539","repositories_listed":0,"syntology":null},{"url":null,"slug":"sceneverse-scaling-3d-vision-language","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","date":"2024-01-17","arxiv_id":"2401.09340","repositories_listed":0,"syntology":null},{"url":null,"slug":"g-3-lq-marrying-hyperbolic-alignment-with","title":"G^3-LQ: Marrying Hyperbolic Alignment with Explicit Semantic-Geometric Modeling for 3D Visual Grounding","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-clip-driven-language-free-3d-visual","title":"Towards CLIP-driven Language-free 3D Visual Grounding via 2D-3D Relational Enhancement and Consistency","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"viewpoint-aware-visual-grounding-in-3d-scenes","title":"Viewpoint-Aware Visual Grounding in 3D Scenes","date":"2024-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-3d-visual-grounding-based","title":"Weakly-Supervised 3D Visual Grounding based on Visual Linguistic Alignment","date":"2023-12-15","arxiv_id":"2312.09625","repositories_listed":0,"syntology":null},{"url":null,"slug":"three-ways-to-improve-verbo-visual-fusion-for","title":"Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding","date":"2023-09-08","arxiv_id":"2309.04561","repositories_listed":0,"syntology":null},{"url":null,"slug":"3drp-net-3d-relative-position-aware-network","title":"3DRP-Net: 3D Relative Position-aware Network for 3D Visual Grounding","date":"2023-07-25","arxiv_id":"2307.13363","repositories_listed":0,"syntology":null},{"url":null,"slug":"viewrefer-grasp-the-multi-view-knowledge-for-1","title":"ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unit3d-a-unified-transformer-for-3d-dense","title":"UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding","date":"2022-12-01","arxiv_id":"2212.00836","repositories_listed":0,"syntology":null},{"url":"/paper/d3net-a-speaker-listener-architecture-for","slug":"d3net-a-speaker-listener-architecture-for","title":"D3Net: A Unified Speaker-Listener Architecture for 3D Dense Captioning and Visual Grounding","date":"2021-12-02","arxiv_id":"2112.01551","repositories_listed":0,"syntology":null},{"url":null,"slug":"transrefer3d-entity-and-relation-aware","title":"TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding","date":"2021-08-05","arxiv_id":"2108.02388","repositories_listed":0,"syntology":null},{"url":null,"slug":"languagerefer-spatial-language-model-for-3d","title":"LanguageRefer: Spatial-Language Model for 3D Visual Grounding","date":"2021-07-07","arxiv_id":"2107.03438","repositories_listed":0,"syntology":null}],"syntology_records":19,"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":19,"papers_where_code_ran_first_page":"/task/3d-visual-grounding/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":"ran","page":1,"of":1,"url":"/task/3d-visual-grounding/papers/ran/1","json":"/task/3d-visual-grounding/papers/ran/1.json","rows":19}],"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":"fc053ce9c1e460252010d33bd7dfa51b9cc27a987e5b7196090f6eb8c26e48a3","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}