{"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/context-modeling-in-3d-human-pose-estimation","title":"Context Modeling in 3D Human Pose Estimation: A Unified Perspective","arxiv_id":"2103.15507","date":"2021-03-29","proceeding":"CVPR 2021 1","authors":["Xiaoxuan Ma","Jiajun Su","Chunyu Wang","Hai Ci","Yizhou Wang"],"abstract":"Estimating 3D human pose from a single image suffers from severe ambiguity since multiple 3D joint configurations may have the same 2D projection. The state-of-the-art methods often rely on context modeling methods such as pictorial structure model (PSM) or graph neural network (GNN) to reduce ambiguity. However, there is no study that rigorously compares them side by side. So we first present a general formula for context modeling in which both PSM and GNN are its special cases. By comparing the two methods, we found that the end-to-end training scheme in GNN and the limb length constraints in PSM are two complementary factors to improve results. To combine their advantages, we propose ContextPose based on attention mechanism that allows enforcing soft limb length constraints in a deep network. The approach effectively reduces the chance of getting absurd 3D pose estimates with incorrect limb lengths and achieves state-of-the-art results on two benchmark datasets. More importantly, the introduction of limb length constraints into deep networks enables the approach to achieve much better generalization performance.","url_abs":"https://arxiv.org/abs/2103.15507v2","url_pdf":"https://arxiv.org/pdf/2103.15507v2.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":"context-modeling-in-3d-human-pose-estimation","repo_url":"https://github.com/ShirleyMaxx/ContextPose-PyTorch-release","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"graph-neural-network","task_name":"Graph Neural Network"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"graph-neural-network","method_name":"Graph Neural Network"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-human36m","task":"3D Human Pose Estimation","dataset":"Human3.6M","model":"ContextPose","rank_in_archive_order":29,"of":88,"metrics":{"Average MPJPE (mm)":"43.4","Multi-View or Monocular":"Monocular","Using 2D ground-truth joints":"No"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-mpi-inf-3dhp","task":"3D Human Pose Estimation","dataset":"MPI-INF-3DHP","model":"ContextPose","rank_in_archive_order":95,"of":108,"metrics":{"AUC":"42.7","PCK":"80.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.15507","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.15507"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/ShirleyMaxx/ContextPose-PyTorch-release","reach":null}],"summary":{"ran":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":"80c5fd10d8f34109","entry":"AttentionConv3D","repo":"ShirleyMaxx/ContextPose-PyTorch-release","repo_kind":"listed","path":"mvn/models/attention_conv_layer.py","file_url":"https://github.com/ShirleyMaxx/ContextPose-PyTorch-release/blob/HEAD/mvn/models/attention_conv_layer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"80c5fd10d8f34109"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}