{"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/3d-human-pose-estimation-with-spatial-and","title":"3D Human Pose Estimation with Spatial and Temporal Transformers","arxiv_id":"2103.10455","date":"2021-03-18","proceeding":"ICCV 2021 10","authors":["Ce Zheng","Sijie Zhu","Matias Mendieta","Taojiannan Yang","Chen Chen","Zhengming Ding"],"abstract":"Transformer architectures have become the model of choice in natural language processing and are now being introduced into computer vision tasks such as image classification, object detection, and semantic segmentation. However, in the field of human pose estimation, convolutional architectures still remain dominant. In this work, we present PoseFormer, a purely transformer-based approach for 3D human pose estimation in videos without convolutional architectures involved. Inspired by recent developments in vision transformers, we design a spatial-temporal transformer structure to comprehensively model the human joint relations within each frame as well as the temporal correlations across frames, then output an accurate 3D human pose of the center frame. We quantitatively and qualitatively evaluate our method on two popular and standard benchmark datasets: Human3.6M and MPI-INF-3DHP. Extensive experiments show that PoseFormer achieves state-of-the-art performance on both datasets. Code is available at \\url{https://github.com/zczcwh/PoseFormer}","url_abs":"https://arxiv.org/abs/2103.10455v3","url_pdf":"https://arxiv.org/pdf/2103.10455v3.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":"3d-human-pose-estimation-with-spatial-and","repo_url":"https://github.com/zczcwh/PoseFormer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"3d-human-pose-estimation-with-spatial-and","repo_url":"https://github.com/thuxyz19/test","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"3d-human-pose-estimation-with-spatial-and","repo_url":"https://github.com/zczcwh/DL-HPE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"monocular-3d-human-pose-estimation","task_name":"Monocular 3D Human Pose Estimation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-human36m","task":"3D Human Pose Estimation","dataset":"Human3.6M","model":"PoseFormer (f=81)","rank_in_archive_order":35,"of":88,"metrics":{"Average MPJPE (mm)":"44.3","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":"PoseFormer","rank_in_archive_order":13,"of":31,"metrics":{"Mean Reconstruction Error (mm)":"21.6"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-mpi-inf-3dhp","task":"3D Human Pose Estimation","dataset":"MPI-INF-3DHP","model":"PoseFormer (9 frames)","rank_in_archive_order":36,"of":108,"metrics":{"AUC":"56.4","MPJPE":"77.1","PCK":"88.6"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-3d-human-pose-estimation-on-human3","task":"Monocular 3D Human Pose Estimation","dataset":"Human3.6M","model":"PoseFormer (T=81)","rank_in_archive_order":15,"of":52,"metrics":{"2D detector":"CPN","Average MPJPE (mm)":"44.3","Frames Needed":"81"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2103.10455","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.10455"}},"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/zczcwh/DL-HPE","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/zczcwh/PoseFormer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thuxyz19/test","reach":null}],"summary":{"ran":4,"unverified":4},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"listed":{"samples":6,"ran":2,"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":8,"samples":[{"code_sha256_prefix":"fab27d0fb962f729","entry":"Attention","repo":"thuxyz19/test","repo_kind":"listed","path":"common/model_poseformer.py","file_url":"https://github.com/thuxyz19/test/blob/HEAD/common/model_poseformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fab27d0fb962f729"}},{"code_sha256_prefix":"806376d9202b2bc9","entry":"Block","repo":"zczcwh/PoseFormer","repo_kind":"official","path":"common/model_poseformer.py","file_url":"https://github.com/zczcwh/PoseFormer/blob/HEAD/common/model_poseformer.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":"806376d9202b2bc9"}},{"code_sha256_prefix":"566d7093b72572b4","entry":"DownSampleAttention","repo":"thuxyz19/test","repo_kind":"listed","path":"common/model_poseformer.py","file_url":"https://github.com/thuxyz19/test/blob/HEAD/common/model_poseformer.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":"566d7093b72572b4"}},{"code_sha256_prefix":"d33650ab39737101","entry":"PoseTransformer","repo":"zczcwh/PoseFormer","repo_kind":"official","path":"common/model_poseformer.py","file_url":"https://github.com/zczcwh/PoseFormer/blob/HEAD/common/model_poseformer.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":"d33650ab39737101"}},{"code_sha256_prefix":"4b147c20666e9018","entry":"Block","repo":"thuxyz19/test","repo_kind":"listed","path":"common/model_poseformer.py","file_url":"https://github.com/thuxyz19/test/blob/HEAD/common/model_poseformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4b147c20666e9018"}},{"code_sha256_prefix":"09d4b28562865d41","entry":"PoseTransformer","repo":"thuxyz19/test","repo_kind":"listed","path":"common/model_poseformer.py","file_url":"https://github.com/thuxyz19/test/blob/HEAD/common/model_poseformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"09d4b28562865d41"}},{"code_sha256_prefix":"5a96e44e698f69e0","entry":"ProbSparseAttention","repo":"thuxyz19/test","repo_kind":"listed","path":"common/model_poseformer.py","file_url":"https://github.com/thuxyz19/test/blob/HEAD/common/model_poseformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5a96e44e698f69e0"}},{"code_sha256_prefix":"3c604929660e9363","entry":"TBlock","repo":"thuxyz19/test","repo_kind":"listed","path":"common/model_poseformer.py","file_url":"https://github.com/thuxyz19/test/blob/HEAD/common/model_poseformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3c604929660e9363"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}