{"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/poseformerv2-exploring-frequency-domain-for","title":"PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation","arxiv_id":"2303.17472","date":"2023-03-30","proceeding":"CVPR 2023 1","authors":["Qitao Zhao","Ce Zheng","Mengyuan Liu","Pichao Wang","Chen Chen"],"abstract":"Recently, transformer-based methods have gained significant success in sequential 2D-to-3D lifting human pose estimation. As a pioneering work, PoseFormer captures spatial relations of human joints in each video frame and human dynamics across frames with cascaded transformer layers and has achieved impressive performance. However, in real scenarios, the performance of PoseFormer and its follow-ups is limited by two factors: (a) The length of the input joint sequence; (b) The quality of 2D joint detection. Existing methods typically apply self-attention to all frames of the input sequence, causing a huge computational burden when the frame number is increased to obtain advanced estimation accuracy, and they are not robust to noise naturally brought by the limited capability of 2D joint detectors. In this paper, we propose PoseFormerV2, which exploits a compact representation of lengthy skeleton sequences in the frequency domain to efficiently scale up the receptive field and boost robustness to noisy 2D joint detection. With minimum modifications to PoseFormer, the proposed method effectively fuses features both in the time domain and frequency domain, enjoying a better speed-accuracy trade-off than its precursor. Extensive experiments on two benchmark datasets (i.e., Human3.6M and MPI-INF-3DHP) demonstrate that the proposed approach significantly outperforms the original PoseFormer and other transformer-based variants. Code is released at \\url{https://github.com/QitaoZhao/PoseFormerV2}.","url_abs":"https://arxiv.org/abs/2303.17472v1","url_pdf":"https://arxiv.org/pdf/2303.17472v1.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":"poseformerv2-exploring-frequency-domain-for","repo_url":"https://github.com/qitaozhao/poseformerv2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"poseformerv2-exploring-frequency-domain-for","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":"classification-1","task_name":"Classification"},{"task_slug":"human-dynamics","task_name":"Human Dynamics"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-mpi-inf-3dhp","task":"3D Human Pose Estimation","dataset":"MPI-INF-3DHP","model":"PoseFormerV2 (T=81)","rank_in_archive_order":10,"of":108,"metrics":{"AUC":"78.8","MPJPE":"27.8","PCK":"97.9"},"uses_additional_data":false},{"leaderboard":"/sota/classification-on-full-body-parkinsons","task":"Classification","dataset":"Full-body Parkinson’s disease dataset","model":"PoseFormerV2","rank_in_archive_order":1,"of":7,"metrics":{"F1-score (weighted)":"0.59"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.17472","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.17472"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qitaozhao/poseformerv2","reach":null}],"summary":{"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":0,"samples":[{"code_sha256_prefix":"9af3eb132594e510","entry":"Attention","repo":"qitaozhao/poseformerv2","repo_kind":"official","path":"mpi_inf_3dhp/model/model_poseformerv2.py","file_url":"https://github.com/qitaozhao/poseformerv2/blob/HEAD/mpi_inf_3dhp/model/model_poseformerv2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9af3eb132594e510"}},{"code_sha256_prefix":"b3bc3259dcec516c","entry":"Block","repo":"qitaozhao/poseformerv2","repo_kind":"official","path":"mpi_inf_3dhp/model/model_poseformerv2.py","file_url":"https://github.com/qitaozhao/poseformerv2/blob/HEAD/mpi_inf_3dhp/model/model_poseformerv2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b3bc3259dcec516c"}},{"code_sha256_prefix":"872f349e099a1f4c","entry":"FreqMlp","repo":"qitaozhao/poseformerv2","repo_kind":"official","path":"mpi_inf_3dhp/model/model_poseformerv2.py","file_url":"https://github.com/qitaozhao/poseformerv2/blob/HEAD/mpi_inf_3dhp/model/model_poseformerv2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"872f349e099a1f4c"}},{"code_sha256_prefix":"d95449711638de93","entry":"MixedBlock","repo":"qitaozhao/poseformerv2","repo_kind":"official","path":"mpi_inf_3dhp/model/model_poseformerv2.py","file_url":"https://github.com/qitaozhao/poseformerv2/blob/HEAD/mpi_inf_3dhp/model/model_poseformerv2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d95449711638de93"}},{"code_sha256_prefix":"a1715055832f71fd","entry":"Mlp","repo":"qitaozhao/poseformerv2","repo_kind":"official","path":"mpi_inf_3dhp/model/model_poseformerv2.py","file_url":"https://github.com/qitaozhao/poseformerv2/blob/HEAD/mpi_inf_3dhp/model/model_poseformerv2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a1715055832f71fd"}},{"code_sha256_prefix":"abe2a44aafd92702","entry":"Model","repo":"qitaozhao/poseformerv2","repo_kind":"official","path":"mpi_inf_3dhp/model/model_poseformerv2.py","file_url":"https://github.com/qitaozhao/poseformerv2/blob/HEAD/mpi_inf_3dhp/model/model_poseformerv2.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":"abe2a44aafd92702"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}