{"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/a-simple-yet-effective-baseline-for-3d-human","title":"A simple yet effective baseline for 3d human pose estimation","arxiv_id":"1705.03098","date":"2017-05-08","proceeding":"ICCV 2017 10","authors":["Julieta Martinez","Rayat Hossain","Javier Romero","James J. Little"],"abstract":"Following the success of deep convolutional networks, state-of-the-art\nmethods for 3d human pose estimation have focused on deep end-to-end systems\nthat predict 3d joint locations given raw image pixels. Despite their excellent\nperformance, it is often not easy to understand whether their remaining error\nstems from a limited 2d pose (visual) understanding, or from a failure to map\n2d poses into 3-dimensional positions. With the goal of understanding these\nsources of error, we set out to build a system that given 2d joint locations\npredicts 3d positions. Much to our surprise, we have found that, with current\ntechnology, \"lifting\" ground truth 2d joint locations to 3d space is a task\nthat can be solved with a remarkably low error rate: a relatively simple deep\nfeed-forward network outperforms the best reported result by about 30\\% on\nHuman3.6M, the largest publicly available 3d pose estimation benchmark.\nFurthermore, training our system on the output of an off-the-shelf\nstate-of-the-art 2d detector (\\ie, using images as input) yields state of the\nart results -- this includes an array of systems that have been trained\nend-to-end specifically for this task. Our results indicate that a large\nportion of the error of modern deep 3d pose estimation systems stems from their\nvisual analysis, and suggests directions to further advance the state of the\nart in 3d human pose estimation.","url_abs":"http://arxiv.org/abs/1705.03098v2","url_pdf":"http://arxiv.org/pdf/1705.03098v2.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":"a-simple-yet-effective-baseline-for-3d-human","repo_url":"https://github.com/una-dinosauria/3d-pose-baseline","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"a-simple-yet-effective-baseline-for-3d-human","repo_url":"https://github.com/SJTU-DL-lab/3d-pose-baseline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-simple-yet-effective-baseline-for-3d-human","repo_url":"https://github.com/ZHONGCHUYUN/3d_pose_baseline_tf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-simple-yet-effective-baseline-for-3d-human","repo_url":"https://github.com/ailingzengzzz/Split-and-Recombine-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-simple-yet-effective-baseline-for-3d-human","repo_url":"https://github.com/denilson020898/baseline_3d_pose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"a-simple-yet-effective-baseline-for-3d-human","repo_url":"https://github.com/garyzhao/SemGCN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"a-simple-yet-effective-baseline-for-3d-human","repo_url":"https://github.com/happyvictor008/High-order-GNN-LF-iter","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"a-simple-yet-effective-baseline-for-3d-human","repo_url":"https://github.com/jaroslaw1007/Pose_Baseline_3D_PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"a-simple-yet-effective-baseline-for-3d-human","repo_url":"https://github.com/llSourcell/3D_Pose_Estimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"a-simple-yet-effective-baseline-for-3d-human","repo_url":"https://github.com/serviceberry3/3d-pose-baseline_android","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"a-simple-yet-effective-baseline-for-3d-human","repo_url":"https://github.com/sidify/3d-pose-estimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"a-simple-yet-effective-baseline-for-3d-human","repo_url":"https://github.com/sidsunny/human-pose-estimation-mlsp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"a-simple-yet-effective-baseline-for-3d-human","repo_url":"https://github.com/zhimingzo/modulated-gcn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"a-simple-yet-effective-baseline-for-3d-human","repo_url":"https://github.com/open-mmlab/mmpose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"3d-pose-estimation","task_name":"3D Pose Estimation"},{"task_slug":"monocular-3d-human-pose-estimation","task_name":"Monocular 3D Human Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-3dpw","task":"3D Human Pose Estimation","dataset":"3DPW","model":"Simple-baseline","rank_in_archive_order":113,"of":119,"metrics":{"PA-MPJPE":"157.0"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-human36m","task":"3D Human Pose Estimation","dataset":"Human3.6M","model":"SIM (SH detections FT) (MA)","rank_in_archive_order":85,"of":88,"metrics":{"Average MPJPE (mm)":"62.9","Multi-View or Monocular":"Monocular","Using 2D ground-truth joints":"No"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-humaneva-i","task":"3D Human Pose Estimation","dataset":"HumanEva-I","model":"SIM (SH detections)","rank_in_archive_order":20,"of":31,"metrics":{"Mean Reconstruction Error (mm)":"24.6"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-3d-human-pose-estimation-on-human3","task":"Monocular 3D Human Pose Estimation","dataset":"Human3.6M","model":"SIM (SH detections FT) (MA)","rank_in_archive_order":31,"of":52,"metrics":{"Average MPJPE (mm)":"62.9","Frames Needed":"1","Need Ground Truth 2D Pose":"No","Use Video Sequence":"No"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.03098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.03098"}},"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/open-mmlab/mmpose","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sidify/3d-pose-estimation","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sidsunny/human-pose-estimation-mlsp","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/una-dinosauria/3d-pose-baseline","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/garyzhao/SemGCN","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jaroslaw1007/Pose_Baseline_3D_PyTorch","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhimingzo/modulated-gcn","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZHONGCHUYUN/3d_pose_baseline_tf","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/happyvictor008/High-order-GNN-LF-iter","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/llSourcell/3D_Pose_Estimation","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SJTU-DL-lab/3d-pose-baseline","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ailingzengzzz/Split-and-Recombine-Net","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/serviceberry3/3d-pose-baseline_android","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/denilson020898/baseline_3d_pose","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":4,"ran_violates":1,"unverified":2},"by_repo_kind":{"listed":{"samples":7,"ran":5,"repositories":3}},"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":0,"samples":[{"code_sha256_prefix":"c9e9ff520e9b4533","entry":"angle_between","repo":"sidify/3d-pose-estimation","repo_kind":"listed","path":"src/kinematics.py","file_url":"https://github.com/sidify/3d-pose-estimation/blob/HEAD/src/kinematics.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c9e9ff520e9b4533"}},{"code_sha256_prefix":"2b344ab200743c2d","entry":"dotproduct","repo":"sidify/3d-pose-estimation","repo_kind":"listed","path":"src/kinematics.py","file_url":"https://github.com/sidify/3d-pose-estimation/blob/HEAD/src/kinematics.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b344ab200743c2d"}},{"code_sha256_prefix":"f5eee6f4a7a2d3ce","entry":"get_action_subset","repo":"sidify/3d-pose-estimation","repo_kind":"listed","path":"src/predict_3dpose.py","file_url":"https://github.com/sidify/3d-pose-estimation/blob/HEAD/src/predict_3dpose.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f5eee6f4a7a2d3ce"}},{"code_sha256_prefix":"c98211090c8cd833","entry":"length","repo":"sidify/3d-pose-estimation","repo_kind":"listed","path":"src/kinematics.py","file_url":"https://github.com/sidify/3d-pose-estimation/blob/HEAD/src/kinematics.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c98211090c8cd833"}},{"code_sha256_prefix":"a5dc69f01bac53c1","entry":"show_anim_curves","repo":"ZHONGCHUYUN/3d_pose_baseline_tf","repo_kind":"listed","path":"src/openpose_3dpose_sandbox.py","file_url":"https://github.com/ZHONGCHUYUN/3d_pose_baseline_tf/blob/HEAD/src/openpose_3dpose_sandbox.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a5dc69f01bac53c1"}},{"code_sha256_prefix":"9088d315ea27a453","entry":"normalization_stats","repo":"SJTU-DL-lab/3d-pose-baseline","repo_kind":"listed","path":"src/data_utils.py","file_url":"https://github.com/SJTU-DL-lab/3d-pose-baseline/blob/HEAD/src/data_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9088d315ea27a453"}},{"code_sha256_prefix":"6bbbd96794d5994d","entry":"read_openpose_json","repo":"ZHONGCHUYUN/3d_pose_baseline_tf","repo_kind":"listed","path":"src/openpose_3dpose_sandbox.py","file_url":"https://github.com/ZHONGCHUYUN/3d_pose_baseline_tf/blob/HEAD/src/openpose_3dpose_sandbox.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6bbbd96794d5994d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}