{"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":"/dataset/pix3d","name":"Pix3D","full_name":null,"description_markdown":"The **Pix3D** dataset is a large-scale benchmark of diverse image-shape pairs with pixel-level 2D-3D alignment. Pix3D has wide applications in shape-related tasks including reconstruction, retrieval, viewpoint estimation, etc.\r\n\r\nSource: [http://pix3d.csail.mit.edu/](http://pix3d.csail.mit.edu/)\r\nImage Source: [http://pix3d.csail.mit.edu/](http://pix3d.csail.mit.edu/)","description_withheld":null,"homepage":"http://pix3d.csail.mit.edu/","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/pix3d-dataset-and-methods-for-single-image-3d","title":"Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling","first_author":"Xingyuan Sun","url":null},"license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"3D","url":"/datasets/modality/3d"}],"tasks":[{"name":"Pose Estimation","url":"/task/pose-estimation","datasets_with_task":"/datasets/task/pose-estimation"},{"name":"3D Shape Reconstruction","url":"/task/3d-shape-reconstruction","datasets_with_task":"/datasets/task/3d-shape-reconstruction"},{"name":"3D Shape Modeling","url":"/task/3d-shape-modeling","datasets_with_task":"/datasets/task/3d-shape-modeling"},{"name":"3D Shape Classification","url":"/task/3d-shape-retrieval","datasets_with_task":"/datasets/task/3d-shape-retrieval"}],"languages":[],"variants":["Pix3D S2","Pix3D S1","Pix3D"],"data_loaders":[],"num_papers_in_archive":142,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/3d-shape-reconstruction-on-pix3d","task":"3D Shape Reconstruction","dataset_variant":"Pix3D","rows":5,"metrics":["CD","EMD","IoU"],"first_row_in_archive_order":{"model":"IM3D","paper":"/paper/holistic-3d-scene-understanding-from-a-single-1","metrics":{"CD":"0.0672","EMD":"N/A","IoU":"N/A"},"code_links":[{"title":"chengzhag/Implicit3DUnderstanding","url":"https://github.com/chengzhag/Implicit3DUnderstanding"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-shape-retrieval-on-pix3d","task":"3D Shape Classification","dataset_variant":"Pix3D","rows":3,"metrics":["R@1","R@16","R@2","R@32","R@4","R@8"],"first_row_in_archive_order":{"model":"MarrNet extension (w/o Pose)","paper":"/paper/pix3d-dataset-and-methods-for-single-image-3d","metrics":{"R@1":"0.53","R@16":"0.85","R@2":"0.62","R@32":"0.90","R@4":"0.71","R@8":"0.78"},"code_links":[{"title":"xingyuansun/pix3d","url":"https://github.com/xingyuansun/pix3d"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-shape-modeling-on-pix3d-s1","task":"3D Shape Modeling","dataset_variant":"Pix3D S1","rows":1,"metrics":["box AP","mask AP","mesh AP"],"first_row_in_archive_order":{"model":"Mesh R-CNN","paper":"/paper/mesh-r-cnn","metrics":{"box AP":"94.0","mask AP":"88.4","mesh AP":"51.1"},"code_links":[{"title":"facebookresearch/pytorch3d","url":"https://github.com/facebookresearch/pytorch3d"},{"title":"facebookresearch/meshrcnn","url":"https://github.com/facebookresearch/meshrcnn"},{"title":"huang229/auto_tooth_arrangement","url":"https://github.com/huang229/auto_tooth_arrangement"},{"title":"IMAC-projects/mesh-deformation","url":"https://github.com/IMAC-projects/mesh-deformation"},{"title":"Penguinazor/mse.wem.project","url":"https://github.com/Penguinazor/mse.wem.project"},{"title":"theycallmepeter/pytorch3d_PBR","url":"https://github.com/theycallmepeter/pytorch3d_PBR"},{"title":"xhxuciedu/3DHand","url":"https://github.com/xhxuciedu/3DHand"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-shape-modeling-on-pix3d-s2","task":"3D Shape Modeling","dataset_variant":"Pix3D S2","rows":1,"metrics":["box AP","mask AP","mesh AP"],"first_row_in_archive_order":{"model":"Mesh R-CNN","paper":"/paper/mesh-r-cnn","metrics":{"box AP":"72.2","mask AP":"63.9 ","mesh AP":"28.8"},"code_links":[{"title":"facebookresearch/pytorch3d","url":"https://github.com/facebookresearch/pytorch3d"},{"title":"facebookresearch/meshrcnn","url":"https://github.com/facebookresearch/meshrcnn"},{"title":"huang229/auto_tooth_arrangement","url":"https://github.com/huang229/auto_tooth_arrangement"},{"title":"IMAC-projects/mesh-deformation","url":"https://github.com/IMAC-projects/mesh-deformation"},{"title":"Penguinazor/mse.wem.project","url":"https://github.com/Penguinazor/mse.wem.project"},{"title":"theycallmepeter/pytorch3d_PBR","url":"https://github.com/theycallmepeter/pytorch3d_PBR"},{"title":"xhxuciedu/3DHand","url":"https://github.com/xhxuciedu/3DHand"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/pose-estimation-on-pix3d","task":"Pose Estimation","dataset_variant":"Pix3D","rows":1,"metrics":["Percentage correct"],"first_row_in_archive_order":{"model":"Mid-Level based","paper":"/paper/object-pose-estimation-using-mid-level-visual","metrics":{"Percentage correct":"74.55"},"code_links":[{"title":"n-nejatishahidin/pose_from_mid-level","url":"https://github.com/n-nejatishahidin/pose_from_mid-level"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":9,"of":9,"counts":{"papers_with_a_benchmark_row":9,"with_a_code_link":8,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":9,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":0,"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 with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/holistic-3d-scene-understanding-from-a-single-1","slug":"holistic-3d-scene-understanding-from-a-single-1","title":"Holistic 3D Scene Understanding from a Single Image with Implicit Representation","date":"2021-03-11","arxiv_id":"2103.06422","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/total3dunderstanding-joint-layout-object-pose","slug":"total3dunderstanding-joint-layout-object-pose","title":"Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image","date":"2020-02-27","arxiv_id":"2002.12212","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["yinyunie/Total3DUnderstanding"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/total3dunderstanding-joint-layout-object-pose#ran","syntology_url":"https://syntology.ai/paper/2002.12212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.12212"}}}},{"paper":"/paper/deep-mesh-reconstruction-from-single-rgb","slug":"deep-mesh-reconstruction-from-single-rgb","title":"Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networks","date":"2019-09-01","arxiv_id":"1909.00321","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":1,"official":{"repos":["jnypan/TMNet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-mesh-reconstruction-from-single-rgb#ran","syntology_url":"https://syntology.ai/paper/1909.00321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.00321"}}}},{"paper":"/paper/mesh-r-cnn","slug":"mesh-r-cnn","title":"Mesh R-CNN","date":"2019-06-06","arxiv_id":"1906.02739","rows_on_this_dataset":2,"code_links":7,"syntology":null},{"paper":"/paper/pix3d-dataset-and-methods-for-single-image-3d","slug":"pix3d-dataset-and-methods-for-single-image-3d","title":"Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling","date":"2018-04-12","arxiv_id":"1804.04610","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/atlasnet-a-papier-mache-approach-to-learning","slug":"atlasnet-a-papier-mache-approach-to-learning","title":"AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation","date":"2018-02-15","arxiv_id":"1802.05384","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["ThibaultGROUEIX/AtlasNet"],"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":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/atlasnet-a-papier-mache-approach-to-learning#ran","syntology_url":"https://syntology.ai/paper/1802.05384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.05384"}}}},{"paper":"/paper/marrnet-3d-shape-reconstruction-via-25d","slug":"marrnet-3d-shape-reconstruction-via-25d","title":"MarrNet: 3D Shape Reconstruction via 2.5D Sketches","date":"2017-11-08","arxiv_id":"1711.03129","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-a-probabilistic-latent-space-of","slug":"learning-a-probabilistic-latent-space-of","title":"Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling","date":"2016-10-24","arxiv_id":"1610.07584","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-a-probabilistic-latent-space-of#ran","syntology_url":"https://syntology.ai/paper/1610.07584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1610.07584"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/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","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/holistic-3d-scene-understanding-from-a-single-1","slug":"holistic-3d-scene-understanding-from-a-single-1","title":"Holistic 3D Scene Understanding from a Single Image with Implicit Representation","date":"2021-03-11","arxiv_id":"2103.06422","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/total3dunderstanding-joint-layout-object-pose","slug":"total3dunderstanding-joint-layout-object-pose","title":"Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image","date":"2020-02-27","arxiv_id":"2002.12212","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":9,"samples_ran":7,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":0,"samples_unverified":2,"pointer_only_for_licence":0,"official":{"repos":["yinyunie/Total3DUnderstanding"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/total3dunderstanding-joint-layout-object-pose#ran","syntology_url":"https://syntology.ai/paper/2002.12212","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.12212"}}}},{"paper":"/paper/deep-mesh-reconstruction-from-single-rgb","slug":"deep-mesh-reconstruction-from-single-rgb","title":"Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networks","date":"2019-09-01","arxiv_id":"1909.00321","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":12,"samples_ran":8,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":1,"samples_unverified":4,"pointer_only_for_licence":1,"official":{"repos":["jnypan/TMNet"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/deep-mesh-reconstruction-from-single-rgb#ran","syntology_url":"https://syntology.ai/paper/1909.00321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.00321"}}}},{"paper":"/paper/mesh-r-cnn","slug":"mesh-r-cnn","title":"Mesh R-CNN","date":"2019-06-06","arxiv_id":"1906.02739","rows_on_this_dataset":2,"code_links":7,"syntology":null},{"paper":"/paper/pix3d-dataset-and-methods-for-single-image-3d","slug":"pix3d-dataset-and-methods-for-single-image-3d","title":"Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling","date":"2018-04-12","arxiv_id":"1804.04610","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/atlasnet-a-papier-mache-approach-to-learning","slug":"atlasnet-a-papier-mache-approach-to-learning","title":"AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation","date":"2018-02-15","arxiv_id":"1802.05384","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":3,"official":{"repos":["ThibaultGROUEIX/AtlasNet"],"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":["unlocated"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/atlasnet-a-papier-mache-approach-to-learning#ran","syntology_url":"https://syntology.ai/paper/1802.05384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.05384"}}}},{"paper":"/paper/marrnet-3d-shape-reconstruction-via-25d","slug":"marrnet-3d-shape-reconstruction-via-25d","title":"MarrNet: 3D Shape Reconstruction via 2.5D Sketches","date":"2017-11-08","arxiv_id":"1711.03129","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/learning-a-probabilistic-latent-space-of","slug":"learning-a-probabilistic-latent-space-of","title":"Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling","date":"2016-10-24","arxiv_id":"1610.07584","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":2,"samples_ran_instrument_failed":1,"samples_unverified":0,"pointer_only_for_licence":0,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/learning-a-probabilistic-latent-space-of#ran","syntology_url":"https://syntology.ai/paper/1610.07584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1610.07584"}}}}],"papers_where_code_ran":4,"papers_where_code_ran_first_page":"/dataset/pix3d/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/pix3d/papers/ran/1","json":"/dataset/pix3d/papers/ran/1.json","rows":4}],"row_route":"each paper's syntology object 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","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":4,"samples_harvested":27,"samples_ran":21,"samples_constructed":0,"samples_ran_checked":17,"samples_ran_instrument_failed":4,"samples_unverified":6,"pointer_only_for_licence":4,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":4,"papers_with_a_run_with_no_instrument_failure":4,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_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'","samples_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":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"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":[{"leaderboard":"/sota/3d-shape-reconstruction-on-pix3d","since_archive":"/sota/3d-shape-reconstruction-on-pix3d#since-judged","papers_judged":1,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"e966f26eecffbc2783a5a64304acc16eb143f59fbd86eee9ba478670d24ce5c7","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}