{"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/surface-normal-estimation","name":"Surface Normal Estimation","slug":"surface-normal-estimation","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":96,"papers_with_code":46,"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":5,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/nyuv2","name":"NYUv2","full_name":"NYU-Depth V2","num_papers_in_archive":986},{"url":"/dataset/grit","name":"GRIT","full_name":"General Robust Image Task Benchmark","num_papers_in_archive":16},{"url":"/dataset/3d-ken-burns-dataset","name":"3D Ken Burns Dataset","full_name":"","num_papers_in_archive":4},{"url":"/dataset/futurehouse","name":"FutureHouse","full_name":"","num_papers_in_archive":3},{"url":"/dataset/carla2real","name":"CARLA2Real","full_name":"","num_papers_in_archive":1}],"subtasks":[],"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":1,"rows_per_page":100,"shown":96,"of":96,"of_with_code":46,"tagged_in_all":96,"counts":{"archive_papers_tagged":96,"with_a_code_link":46,"where_syntology_ran_a_sample":18,"not_listed_spam_title":0,"listed":96,"listed_where_code_ran":18,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":14,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":14,"listed_every_run_a_failure_of_syntologys_instrument":4,"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/predicting-depth-surface-normals-and-semantic","slug":"predicting-depth-surface-normals-and-semantic","title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","date":"2014-11-18","arxiv_id":"1411.4734","repositories_listed":4,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"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, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/predicting-depth-surface-normals-and-semantic#ran","syntology_url":"https://syntology.ai/paper/1411.4734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1411.4734"}},"official":null}},{"url":"/paper/maintaining-natural-image-statistics-with-the","slug":"maintaining-natural-image-statistics-with-the","title":"Maintaining Natural Image Statistics with the Contextual Loss","date":"2018-03-13","arxiv_id":"1803.04626","repositories_listed":3,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"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) · 2 unverified","sample_list":"/paper/maintaining-natural-image-statistics-with-the#ran","syntology_url":"https://syntology.ai/paper/1803.04626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.04626"}},"official":null}},{"url":"/paper/sapiens-foundation-for-human-vision-models","slug":"sapiens-foundation-for-human-vision-models","title":"Sapiens: Foundation for Human Vision Models","date":"2024-08-22","arxiv_id":"2408.12569","repositories_listed":2,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sapiens-foundation-for-human-vision-models#ran","syntology_url":"https://syntology.ai/paper/2408.12569","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.12569"}},"official":null}},{"url":"/paper/idisc-internal-discretization-for-monocular","slug":"idisc-internal-discretization-for-monocular","title":"iDisc: Internal Discretization for Monocular Depth Estimation","date":"2023-04-13","arxiv_id":"2304.06334","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":2,"n_ran_checked":3,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/idisc-internal-discretization-for-monocular#ran","syntology_url":"https://syntology.ai/paper/2304.06334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.06334"}},"official":{"repos":["SysCV/idisc"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-large-scale-homography-benchmark","slug":"a-large-scale-homography-benchmark","title":"A Large Scale Homography Benchmark","date":"2023-02-20","arxiv_id":"2302.09997","repositories_listed":2,"syntology":null},{"url":"/paper/cross-task-attention-mechanism-for-dense","slug":"cross-task-attention-mechanism-for-dense","title":"DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learning","date":"2022-06-17","arxiv_id":"2206.08927","repositories_listed":2,"syntology":null},{"url":"/paper/geonet-iterative-geometric-neural-network","slug":"geonet-iterative-geometric-neural-network","title":"GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation","date":"2020-12-13","arxiv_id":"2012.06980","repositories_listed":2,"syntology":null},{"url":"/paper/scaling-and-benchmarking-self-supervised","slug":"scaling-and-benchmarking-self-supervised","title":"Scaling and Benchmarking Self-Supervised Visual Representation Learning","date":"2019-05-03","arxiv_id":"1905.01235","repositories_listed":2,"syntology":null},{"url":"/paper/differentiable-iterative-surface-normal","slug":"differentiable-iterative-surface-normal","title":"Deep Iterative Surface Normal Estimation","date":"2019-04-15","arxiv_id":"1904.07172","repositories_listed":2,"syntology":null},{"url":"/paper/spherical-regression-learning-viewpoints","slug":"spherical-regression-learning-viewpoints","title":"Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spheres","date":"2019-04-10","arxiv_id":"1904.05404","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":2,"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: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/spherical-regression-learning-viewpoints#ran","syntology_url":"https://syntology.ai/paper/1904.05404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.05404"}},"official":{"repos":["leoshine/Spherical_Regression"],"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/lisu-a-dataset-and-method-for-lidar-surface-1","slug":"lisu-a-dataset-and-method-for-lidar-surface-1","title":"LiSu: A Dataset and Method for LiDAR Surface Normal Estimation","date":"2025-03-11","arxiv_id":"2503.08601","repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-geometric-estimation-of-depth-and","slug":"multi-task-geometric-estimation-of-depth-and","title":"Multi-task Geometric Estimation of Depth and Surface Normal from Monocular 360° Images","date":"2024-11-04","arxiv_id":"2411.01749","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-image-conditional-diffusion","slug":"fine-tuning-image-conditional-diffusion","title":"Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think","date":"2024-09-17","arxiv_id":"2409.11355","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_constructed":0,"n_ran_checked":11,"n_instrument":5,"n_unverified":1,"n_honours":3,"n_violates":2,"n_no_contract":6,"n_pointer_only":17,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 3 honoured, 2 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fine-tuning-image-conditional-diffusion#ran","syntology_url":"https://syntology.ai/paper/2409.11355","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.11355"}},"official":{"repos":["VisualComputingInstitute/diffusion-e2e-ft"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/metric3d-v2-a-versatile-monocular-geometric-1","slug":"metric3d-v2-a-versatile-monocular-geometric-1","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","date":"2024-03-22","arxiv_id":"2404.15506","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/metric3d-v2-a-versatile-monocular-geometric-1#ran","syntology_url":"https://syntology.ai/paper/2404.15506","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15506"}},"official":{"repos":["yvanyin/metric3d"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusion-models-trained-with-large-data-are","slug":"diffusion-models-trained-with-large-data-are","title":"What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?","date":"2024-03-10","arxiv_id":"2403.06090","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/diffusion-models-trained-with-large-data-are#ran","syntology_url":"https://syntology.ai/paper/2403.06090","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06090"}},"official":{"repos":["aim-uofa/genpercept"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/rethinking-inductive-biases-for-surface","slug":"rethinking-inductive-biases-for-surface","title":"Rethinking Inductive Biases for Surface Normal Estimation","date":"2024-03-01","arxiv_id":"2403.00712","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":5,"n_instrument":2,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/rethinking-inductive-biases-for-surface#ran","syntology_url":"https://syntology.ai/paper/2403.00712","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.00712"}},"official":{"repos":["baegwangbin/dsine"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/polymax-general-dense-prediction-with-mask","slug":"polymax-general-dense-prediction-with-mask","title":"PolyMaX: General Dense Prediction with Mask Transformer","date":"2023-11-09","arxiv_id":"2311.05770","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/polymax-general-dense-prediction-with-mask#ran","syntology_url":"https://syntology.ai/paper/2311.05770","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.05770"}},"official":{"repos":["google-research/deeplab2"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tsp-transformer-task-specific-prompts-boosted","slug":"tsp-transformer-task-specific-prompts-boosted","title":"TSP-Transformer: Task-Specific Prompts Boosted Transformer for Holistic Scene Understanding","date":"2023-11-06","arxiv_id":"2311.03427","repositories_listed":1,"syntology":null},{"url":"/paper/decodable-and-sample-invariant-continuous","slug":"decodable-and-sample-invariant-continuous","title":"Decodable and Sample Invariant Continuous Object Encoder","date":"2023-10-31","arxiv_id":"2311.00187","repositories_listed":1,"syntology":null},{"url":"/paper/found-foot-optimization-with-uncertain","slug":"found-foot-optimization-with-uncertain","title":"FOUND: Foot Optimization with Uncertain Normals for Surface Deformation Using Synthetic Data","date":"2023-10-27","arxiv_id":"2310.18279","repositories_listed":1,"syntology":null},{"url":"/paper/prompt-guided-transformer-for-multi-task","slug":"prompt-guided-transformer-for-multi-task","title":"Prompt Guided Transformer for Multi-Task Dense Prediction","date":"2023-07-28","arxiv_id":"2307.15362","repositories_listed":1,"syntology":null},{"url":"/paper/independent-component-alignment-for-multi-1","slug":"independent-component-alignment-for-multi-1","title":"Independent Component Alignment for Multi-Task Learning","date":"2023-05-30","arxiv_id":"2305.19000","repositories_listed":1,"syntology":null},{"url":"/paper/d2nt-a-high-performing-depth-to-normal","slug":"d2nt-a-high-performing-depth-to-normal","title":"D2NT: A High-Performing Depth-to-Normal Translator","date":"2023-04-24","arxiv_id":"2304.12031","repositories_listed":1,"syntology":null},{"url":"/paper/high-quality-rgb-d-reconstruction-via-multi","slug":"high-quality-rgb-d-reconstruction-via-multi","title":"High-Quality RGB-D Reconstruction via Multi-View Uncalibrated Photometric Stereo and Gradient-SDF","date":"2022-10-21","arxiv_id":"2210.12202","repositories_listed":1,"syntology":null},{"url":"/paper/multi-task-meta-learning-learn-how-to-adapt","slug":"multi-task-meta-learning-learn-how-to-adapt","title":"Multi-Task Meta Learning: learn how to adapt to unseen tasks","date":"2022-10-13","arxiv_id":"2210.06989","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/multi-task-meta-learning-learn-how-to-adapt#ran","syntology_url":"https://syntology.ai/paper/2210.06989","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.06989"}},"official":{"repos":["ricupa/mtml-learn-how-to-adapt-to-unseen-tasks"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/perspective-phase-angle-model-for","slug":"perspective-phase-angle-model-for","title":"Perspective Phase Angle Model for Polarimetric 3D Reconstruction","date":"2022-07-20","arxiv_id":"2207.09629","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/perspective-phase-angle-model-for#ran","syntology_url":"https://syntology.ai/paper/2207.09629","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.09629"}},"official":{"repos":["gcchen97/ppa4p3d"],"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/egocentric-scene-understanding-via-multimodal-1","slug":"egocentric-scene-understanding-via-multimodal-1","title":"Egocentric Scene Understanding via Multimodal Spatial Rectifier","date":"2022-07-14","arxiv_id":"2207.07077","repositories_listed":1,"syntology":null},{"url":"/paper/mult-an-end-to-end-multitask-learning","slug":"mult-an-end-to-end-multitask-learning","title":"MulT: An End-to-End Multitask Learning Transformer","date":"2022-05-17","arxiv_id":"2205.08303","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/mult-an-end-to-end-multitask-learning#ran","syntology_url":"https://syntology.ai/paper/2205.08303","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.08303"}},"official":null}},{"url":"/paper/grit-general-robust-image-task-benchmark","slug":"grit-general-robust-image-task-benchmark","title":"GRIT: General Robust Image Task Benchmark","date":"2022-04-28","arxiv_id":"2204.13653","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/grit-general-robust-image-task-benchmark#ran","syntology_url":"https://syntology.ai/paper/2204.13653","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.13653"}},"official":{"repos":["allenai/grit_official"],"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/inverted-pyramid-multi-task-transformer-for","slug":"inverted-pyramid-multi-task-transformer-for","title":"InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding","date":"2022-03-15","arxiv_id":"2203.07997","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"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) · 2 unverified","sample_list":"/paper/inverted-pyramid-multi-task-transformer-for#ran","syntology_url":"https://syntology.ai/paper/2203.07997","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07997"}},"official":{"repos":["prismformore/InvPT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/object-pose-estimation-using-mid-level-visual","slug":"object-pose-estimation-using-mid-level-visual","title":"Object Pose Estimation using Mid-level Visual Representations","date":"2022-03-02","arxiv_id":"2203.01449","repositories_listed":1,"syntology":null},{"url":"/paper/omnidata-a-scalable-pipeline-for-making-multi-1","slug":"omnidata-a-scalable-pipeline-for-making-multi-1","title":"Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans","date":"2021-10-11","arxiv_id":"2110.04994","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/omnidata-a-scalable-pipeline-for-making-multi-1#ran","syntology_url":"https://syntology.ai/paper/2110.04994","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.04994"}},"official":{"repos":["EPFL-VILAB/Omnidata"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/estimating-and-exploiting-the-aleatoric","slug":"estimating-and-exploiting-the-aleatoric","title":"Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation","date":"2021-09-20","arxiv_id":"2109.09881","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":3,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/estimating-and-exploiting-the-aleatoric#ran","syntology_url":"https://syntology.ai/paper/2109.09881","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.09881"}},"official":{"repos":["baegwangbin/surface_normal_uncertainty"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":3,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/human-pose-and-shape-estimation-from-single","slug":"human-pose-and-shape-estimation-from-single","title":"Human Pose and Shape Estimation from Single Polarization Images","date":"2021-08-15","arxiv_id":"2108.06834","repositories_listed":1,"syntology":null},{"url":"/paper/transformers-solve-the-limited-receptive","slug":"transformers-solve-the-limited-receptive","title":"Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction","date":"2021-03-22","arxiv_id":"2103.12091","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":7,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 7 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified; every one of the 7 samples that ran constructed an object rather than computing a result","sample_list":"/paper/transformers-solve-the-limited-receptive#ran","syntology_url":"https://syntology.ai/paper/2103.12091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.12091"}},"official":{"repos":["ygjwd12345/TransDepth"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/holicity-a-city-scale-data-platform-for","slug":"holicity-a-city-scale-data-platform-for","title":"HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structures","date":"2020-08-07","arxiv_id":"2008.03286","repositories_listed":1,"syntology":null},{"url":"/paper/surface-normal-estimation-of-tilted-images","slug":"surface-normal-estimation-of-tilted-images","title":"Surface Normal Estimation of Tilted Images via Spatial Rectifier","date":"2020-07-17","arxiv_id":"2007.09264","repositories_listed":1,"syntology":null},{"url":"/paper/sharingan-combining-synthetic-and-real-data-1","slug":"sharingan-combining-synthetic-and-real-data-1","title":"SharinGAN: Combining Synthetic and Real Data for Unsupervised Geometry Estimation","date":"2020-06-07","arxiv_id":"2006.04026","repositories_listed":1,"syntology":null},{"url":"/paper/irs-a-large-synthetic-indoor-robotics-stereo","slug":"irs-a-large-synthetic-indoor-robotics-stereo","title":"IRS: A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal Estimation","date":"2019-12-20","arxiv_id":"1912.09678","repositories_listed":1,"syntology":null},{"url":"/paper/deep-surface-normal-estimation-with","slug":"deep-surface-normal-estimation-with","title":"Deep Surface Normal Estimation with Hierarchical RGB-D Fusion","date":"2019-04-06","arxiv_id":"1904.03405","repositories_listed":1,"syntology":null},{"url":"/paper/framenet-learning-local-canonical-frames-of","slug":"framenet-learning-local-canonical-frames-of","title":"FrameNet: Learning Local Canonical Frames of 3D Surfaces from a Single RGB Image","date":"2019-03-29","arxiv_id":"1903.12305","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-multi-task-learning-with-rock-a","slug":"revisiting-multi-task-learning-with-rock-a","title":"Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection","date":"2018-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/geonet-geometric-neural-network-for-joint","slug":"geonet-geometric-neural-network-for-joint","title":"GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation","date":"2018-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pixel-wise-attentional-gating-for","slug":"pixel-wise-attentional-gating-for","title":"Pixel-wise Attentional Gating for Parsimonious Pixel Labeling","date":"2018-05-03","arxiv_id":"1805.01556","repositories_listed":1,"syntology":null},{"url":"/paper/generic-3d-representation-via-pose-estimation","slug":"generic-3d-representation-via-pose-estimation","title":"Generic 3D Representation via Pose Estimation and Matching","date":"2017-10-23","arxiv_id":"1710.08247","repositories_listed":1,"syntology":null},{"url":"/paper/pixelnet-representation-of-the-pixels-by-the","slug":"pixelnet-representation-of-the-pixels-by-the","title":"PixelNet: Representation of the pixels, by the pixels, and for the pixels","date":"2017-02-21","arxiv_id":"1702.06506","repositories_listed":1,"syntology":null},{"url":null,"slug":"probabilistic-online-event-downsampling","title":"Probabilistic Online Event Downsampling","date":"2025-06-03","arxiv_id":"2506.02547","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-and-real-time-surface-normal","title":"Robust and Real-time Surface Normal Estimation from Stereo Disparities using Affine Transformations","date":"2025-04-21","arxiv_id":"2504.15121","repositories_listed":0,"syntology":null},{"url":null,"slug":"normalcrafter-learning-temporally-consistent","title":"NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors","date":"2025-04-15","arxiv_id":"2504.11427","repositories_listed":0,"syntology":null},{"url":null,"slug":"image-gradient-aided-photometric-stereo","title":"Image Gradient-Aided Photometric Stereo Network","date":"2024-12-16","arxiv_id":"2412.11650","repositories_listed":0,"syntology":null},{"url":null,"slug":"elite360m-efficient-360-multi-task-learning","title":"Elite360M: Efficient 360 Multi-task Learning via Bi-projection Fusion and Cross-task Collaboration","date":"2024-08-18","arxiv_id":"2408.09336","repositories_listed":0,"syntology":null},{"url":null,"slug":"stablenormal-reducing-diffusion-variance-for","title":"StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal","date":"2024-06-24","arxiv_id":"2406.16864","repositories_listed":0,"syntology":null},{"url":null,"slug":"enabling-visual-recognition-at-radio","title":"Enabling Visual Recognition at Radio Frequency","date":"2024-05-29","arxiv_id":"2405.19516","repositories_listed":0,"syntology":null},{"url":null,"slug":"panonormal-monocular-indoor-360deg-surface","title":"PanoNormal: Monocular Indoor 360° Surface Normal Estimation","date":"2024-05-29","arxiv_id":"2405.18745","repositories_listed":0,"syntology":null},{"url":null,"slug":"region-aware-distribution-contrast-a-novel","title":"Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning","date":"2024-03-15","arxiv_id":"2403.10252","repositories_listed":0,"syntology":null},{"url":null,"slug":"surface-normal-estimation-with-transformers","title":"Surface Normal Estimation with Transformers","date":"2024-01-11","arxiv_id":"2401.05745","repositories_listed":0,"syntology":null},{"url":null,"slug":"event-based-shape-from-polarization-with","title":"Event-based Shape from Polarization with Spiking Neural Networks","date":"2023-12-26","arxiv_id":"2312.16071","repositories_listed":0,"syntology":null},{"url":null,"slug":"rftrans-leveraging-refractive-flow-of","title":"RFTrans: Leveraging Refractive Flow of Transparent Objects for Surface Normal Estimation and Manipulation","date":"2023-11-21","arxiv_id":"2311.12398","repositories_listed":0,"syntology":null},{"url":null,"slug":"clip-meets-model-zoo-experts-pseudo","title":"CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement","date":"2023-10-21","arxiv_id":"2310.14108","repositories_listed":0,"syntology":null},{"url":"/paper/large-scale-monocular-depth-estimation-in-the","slug":"large-scale-monocular-depth-estimation-in-the","title":"Large-scale Monocular Depth Estimation in the Wild","date":"2023-09-18","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"transnet-transparent-object-manipulation","title":"TransNet: Transparent Object Manipulation Through Category-Level Pose Estimation","date":"2023-07-23","arxiv_id":"2307.12400","repositories_listed":0,"syntology":null},{"url":null,"slug":"pointersect-neural-rendering-with-cloud-ray","title":"Pointersect: Neural Rendering with Cloud-Ray Intersection","date":"2023-04-24","arxiv_id":"2304.12390","repositories_listed":0,"syntology":null},{"url":null,"slug":"event-fusion-photometric-stereo-network","title":"Event Fusion Photometric Stereo Network","date":"2023-03-01","arxiv_id":"2303.00308","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-large-scale-homography-benchmark-1","title":"A Large-Scale Homography Benchmark","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"core-co-planarity-regularized-monocular","title":"CORE: Co-planarity Regularized Monocular Geometry Estimation with Weak Supervision","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"diligent-pi-photometric-stereo-for-planar","title":"DiLiGenT-Pi: Photometric Stereo for Planar Surfaces with Rich Details - Benchmark Dataset and Beyond","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-globally-optimal-surface-normal","title":"Fast Globally Optimal Surface Normal Estimation from an Affine Correspondence","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-learning-with-knowledge","title":"Multi-Task Learning with Knowledge Distillation for Dense Prediction","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"releaps-reinforcement-learning-based","title":"ReLeaPS : Reinforcement Learning-based Illumination Planning for Generalized Photometric Stereo","date":"2023-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-accurate-and-object-boundary-aware","title":"Fast, Accurate and Object Boundary-Aware Surface Normal Estimation from Depth Maps","date":"2022-09-17","arxiv_id":"2209.08241","repositories_listed":0,"syntology":null},{"url":null,"slug":"transnet-category-level-transparent-object","title":"TransNet: Category-Level Transparent Object Pose Estimation","date":"2022-08-22","arxiv_id":"2208.10002","repositories_listed":0,"syntology":null},{"url":null,"slug":"sda-sne-spatial-discontinuity-aware-surface","title":"SDA-SNE: Spatial Discontinuity-Aware Surface Normal Estimation via Multi-Directional Dynamic Programming","date":"2022-08-18","arxiv_id":"2208.08667","repositories_listed":0,"syntology":null},{"url":"/paper/unified-io-a-unified-model-for-vision","slug":"unified-io-a-unified-model-for-vision","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","date":"2022-06-17","arxiv_id":"2206.08916","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-rgb-scene-property-synthesis-with","title":"Beyond RGB: Scene-Property Synthesis with Neural Radiance Fields","date":"2022-06-09","arxiv_id":"2206.04669","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-self-training-for-learning-general","title":"Multi-Task Self-Training for Learning General Representations","date":"2021-08-25","arxiv_id":"2108.11353","repositories_listed":0,"syntology":null},{"url":null,"slug":"sne-roadseg-rethinking-depth-normal","title":"SNE-RoadSeg+: Rethinking Depth-Normal Translation and Deep Supervision for Freespace Detection","date":"2021-07-30","arxiv_id":"2107.14599","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-image-depth-estimation-an-overview","title":"Single Image Depth Estimation: An Overview","date":"2021-04-13","arxiv_id":"2104.06456","repositories_listed":0,"syntology":null},{"url":null,"slug":"streaming-self-training-via-domain-agnostic","title":"Streaming Self-Training via Domain-Agnostic Unlabeled Images","date":"2021-04-07","arxiv_id":"2104.03309","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-surface-normal-estimation-on-the-2","title":"Deep Surface Normal Estimation on the 2-Sphere with Confidence Guided Semantic Attention","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"simpose-effectively-learning-densepose-and-1","title":"SimPose: Effectively Learning DensePose and Surface Normals of People from Simulated Data","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"what-is-learned-in-deep-uncalibrated","title":"What is Learned in Deep Uncalibrated Photometric Stereo?","date":"2020-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"simpose-effectively-learning-densepose-and","title":"SimPose: Effectively Learning DensePose and Surface Normals of People from Simulated Data","date":"2020-07-30","arxiv_id":"2007.15506","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-task-specific-representation-via-1m","title":"Improving task-specific representation via 1M unlabelled images without any extra knowledge","date":"2020-06-24","arxiv_id":"2006.13919","repositories_listed":0,"syntology":null},{"url":null,"slug":"attentive-feature-reuse-for-multi-task-meta","title":"Attentive Feature Reuse for Multi Task Meta learning","date":"2020-06-12","arxiv_id":"2006.07438","repositories_listed":0,"syntology":null},{"url":null,"slug":"vplnet-deep-single-view-normal-estimation","title":"VPLNet: Deep Single View Normal Estimation With Vanishing Points and Lines","date":"2020-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"visualechoes-spatial-image-representation","title":"VisualEchoes: Spatial Image Representation Learning through Echolocation","date":"2020-05-04","arxiv_id":"2005.01616","repositories_listed":0,"syntology":null},{"url":null,"slug":"anchor-tasks-inexpensive-shared-and-aligned","title":"Task-Assisted Domain Adaptation with Anchor Tasks","date":"2019-08-16","arxiv_id":"1908.06079","repositories_listed":0,"syntology":null},{"url":null,"slug":"pano-popups-indoor-3d-reconstruction-with-a","title":"Pano Popups: Indoor 3D Reconstruction with a Plane-Aware Network","date":"2019-07-01","arxiv_id":"1907.00939","repositories_listed":0,"syntology":null},{"url":"/paper/self-supervised-learning-for-single-view","slug":"self-supervised-learning-for-single-view","title":"Self-supervised Learning for Single View Depth and Surface Normal Estimation","date":"2019-03-01","arxiv_id":"1903.00112","repositories_listed":0,"syntology":null},{"url":null,"slug":"transitive-invariance-for-self-supervised","title":"Transitive Invariance for Self-supervised Visual Representation Learning","date":"2017-08-09","arxiv_id":"1708.02901","repositories_listed":0,"syntology":null},{"url":null,"slug":"pano2cad-room-layout-from-a-single-panorama","title":"Pano2CAD: Room Layout From A Single Panorama Image","date":"2016-09-29","arxiv_id":"1609.09270","repositories_listed":0,"syntology":null},{"url":null,"slug":"pixelnet-towards-a-general-pixel-level","title":"PixelNet: Towards a General Pixel-level Architecture","date":"2016-09-21","arxiv_id":"1609.06694","repositories_listed":0,"syntology":null},{"url":null,"slug":"fine-scale-surface-normal-estimation-using-a","title":"Fine-scale Surface Normal Estimation using a Single NIR Image","date":"2016-03-24","arxiv_id":"1603.07475","repositories_listed":0,"syntology":null},{"url":null,"slug":"depth-and-surface-normal-estimation-from","title":"Depth and Surface Normal Estimation From Monocular Images Using Regression on Deep Features and Hierarchical CRFs","date":"2015-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-learning-of-visual","title":"Unsupervised Learning of Visual Representations using Videos","date":"2015-05-04","arxiv_id":"1505.00687","repositories_listed":0,"syntology":null},{"url":null,"slug":"designing-deep-networks-for-surface-normal","title":"Designing Deep Networks for Surface Normal Estimation","date":"2014-11-18","arxiv_id":"1411.4958","repositories_listed":0,"syntology":null}],"syntology_records":18,"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":18,"papers_where_code_ran_first_page":"/task/surface-normal-estimation/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/surface-normal-estimation/papers/ran/1","json":"/task/surface-normal-estimation/papers/ran/1.json","rows":18}],"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":"475155455db77fbe1ff5f8f2f2ed775ef214648092d027d0458676e144cec076","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}