{"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":"/paper/learning-to-reconstruct-3d-human-pose-and","title":"Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop","arxiv_id":"1909.12828","date":"2019-09-27","proceeding":"ICCV 2019 10","authors":["Nikos Kolotouros","Georgios Pavlakos","Michael J. Black","Kostas Daniilidis"],"abstract":"Model-based human pose estimation is currently approached through two different paradigms. Optimization-based methods fit a parametric body model to 2D observations in an iterative manner, leading to accurate image-model alignments, but are often slow and sensitive to the initialization. In contrast, regression-based methods, that use a deep network to directly estimate the model parameters from pixels, tend to provide reasonable, but not pixel accurate, results while requiring huge amounts of supervision. In this work, instead of investigating which approach is better, our key insight is that the two paradigms can form a strong collaboration. A reasonable, directly regressed estimate from the network can initialize the iterative optimization making the fitting faster and more accurate. Similarly, a pixel accurate fit from iterative optimization can act as strong supervision for the network. This is the core of our proposed approach SPIN (SMPL oPtimization IN the loop). The deep network initializes an iterative optimization routine that fits the body model to 2D joints within the training loop, and the fitted estimate is subsequently used to supervise the network. Our approach is self-improving by nature, since better network estimates can lead the optimization to better solutions, while more accurate optimization fits provide better supervision for the network. We demonstrate the effectiveness of our approach in different settings, where 3D ground truth is scarce, or not available, and we consistently outperform the state-of-the-art model-based pose estimation approaches by significant margins. The project website with videos, results, and code can be found at https://seas.upenn.edu/~nkolot/projects/spin.","url_abs":"https://arxiv.org/abs/1909.12828v1","url_pdf":"https://arxiv.org/pdf/1909.12828v1.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":"learning-to-reconstruct-3d-human-pose-and","repo_url":"https://github.com/nkolot/SPIN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"3d-human-shape-estimation","task_name":"3D Human Shape Estimation"},{"task_slug":"3d-multi-person-pose-estimation","task_name":"3D Multi-Person Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-3d-poses-in-the","task":"3D Human Pose Estimation","dataset":"3D Poses in the Wild Challenge","model":"SPIN","rank_in_archive_order":3,"of":5,"metrics":{"MPJAE":"25.42","MPJPE":"102.56"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-3dpw","task":"3D Human Pose Estimation","dataset":"3DPW","model":"SPIN","rank_in_archive_order":63,"of":119,"metrics":{"MPJPE":"96.9","MPVPE":"116.4","PA-MPJPE":"59.2"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-agora","task":"3D Human Pose Estimation","dataset":"AGORA","model":"SPIN","rank_in_archive_order":10,"of":11,"metrics":{"B-MPJPE":"175.1","B-MVE":"168.7","B-NMJE":"223.1","B-NMVE":"216.3"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-mpi-inf-3dhp","task":"3D Human Pose Estimation","dataset":"MPI-INF-3DHP","model":"SPIN","rank_in_archive_order":73,"of":108,"metrics":{"AUC":"37.1","MPJPE":"105.2","PCK":"76.4"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-mpi-inf-3dhp","task":"3D Human Pose Estimation","dataset":"MPI-INF-3DHP","model":"SPIN (Rigid Alignment)","rank_in_archive_order":85,"of":108,"metrics":{"AUC":"55.6","PA-MPJPE":"67.5","PCK":"92.5"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-shape-estimation-on-ssp-3d","task":"3D Human Shape Estimation","dataset":"SSP-3D","model":"SPIN","rank_in_archive_order":8,"of":11,"metrics":{"PVE-T-SC":"22.2","mIOU":"70.0"},"uses_additional_data":false},{"leaderboard":"/sota/3d-multi-person-pose-estimation-on-agora","task":"3D Multi-Person Pose Estimation","dataset":"AGORA","model":"SPIN","rank_in_archive_order":3,"of":4,"metrics":{"B-MPJPE":"175.1","B-MVE":"168.7","B-NMJE":"223.1","B-NMVE":"216.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1909.12828","atlas_url":"https://app.syntology.ai/?focus=1909.12828","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1909.12828"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1909.12828\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1909.12828"},"call":"get_concepts_for_paper(arxiv_id=\"1909.12828\")"}],"by_repo":[{"repo":"nkolot/SPIN","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"d440b04b46f847fe23990aa8340db3bf0081c7bf17ce657135620e2183f07484","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}