{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/unite-the-people-closing-the-loop-between-3d","title":"Unite the People: Closing the Loop Between 3D and 2D Human Representations","arxiv_id":"1701.02468","date":"2017-01-10","proceeding":"CVPR 2017 7","authors":["Christoph Lassner","Javier Romero","Martin Kiefel","Federica Bogo","Michael J. Black","Peter V. Gehler"],"abstract":"3D models provide a common ground for different representations of human\nbodies. In turn, robust 2D estimation has proven to be a powerful tool to\nobtain 3D fits \"in-the- wild\". However, depending on the level of detail, it\ncan be hard to impossible to acquire labeled data for training 2D estimators on\nlarge scale. We propose a hybrid approach to this problem: with an extended\nversion of the recently introduced SMPLify method, we obtain high quality 3D\nbody model fits for multiple human pose datasets. Human annotators solely sort\ngood and bad fits. This procedure leads to an initial dataset, UP-3D, with rich\nannotations. With a comprehensive set of experiments, we show how this data can\nbe used to train discriminative models that produce results with an\nunprecedented level of detail: our models predict 31 segments and 91 landmark\nlocations on the body. Using the 91 landmark pose estimator, we present\nstate-of-the art results for 3D human pose and shape estimation using an order\nof magnitude less training data and without assumptions about gender or pose in\nthe fitting procedure. We show that UP-3D can be enhanced with these improved\nfits to grow in quantity and quality, which makes the system deployable on\nlarge scale. The data, code and models are available for research purposes.","url_abs":"http://arxiv.org/abs/1701.02468v3","url_pdf":"http://arxiv.org/pdf/1701.02468v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"unite-the-people-closing-the-loop-between-3d","repo_url":"https://github.com/MandyMo/pytorch_HMR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"unite-the-people-closing-the-loop-between-3d","repo_url":"https://github.com/classner/up","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"3d-human-pose-and-shape-estimation","task_name":"3D human pose and shape estimation"},{"task_slug":"monocular-3d-human-pose-estimation","task_name":"Monocular 3D Human Pose Estimation"}],"methods":[],"datasets_introduced":[{"slug":"unite-the-people","name":"Unite the People","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-humaneva-i","task":"3D Human Pose Estimation","dataset":"HumanEva-I","model":"SMPLify (dense)","rank_in_archive_order":30,"of":31,"metrics":{"Mean Reconstruction Error (mm)":"74.5"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-3d-human-pose-estimation-on-human3","task":"Monocular 3D Human Pose Estimation","dataset":"Human3.6M","model":"SMPLify\n(dense)","rank_in_archive_order":43,"of":52,"metrics":{"Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-3d-human-pose-estimation-on-human3","task":"Monocular 3D Human Pose Estimation","dataset":"Human3.6M","model":"SMPLify (dense)","rank_in_archive_order":52,"of":52,"metrics":{"PA-MPJPE":"80.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1701.02468","atlas_url":"https://app.syntology.ai/?focus=1701.02468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1701.02468"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/classner/up","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MandyMo/pytorch_HMR","reach":{"status":"unanswered"}}],"summary":{"ran_fixture":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"fac54f8291d8135c","entry":"pmap_from_mats","repo":"classner/up","repo_kind":"listed","path":"pose/pose.py","file_url":"https://github.com/classner/up/blob/HEAD/pose/pose.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"fac54f8291d8135c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}