{"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/deciwatch-a-simple-baseline-for-10x-efficient","title":"DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation","arxiv_id":"2203.08713","date":"2022-03-16","proceeding":null,"authors":["Ailing Zeng","Xuan Ju","Lei Yang","Ruiyuan Gao","Xizhou Zhu","Bo Dai","Qiang Xu"],"abstract":"This paper proposes a simple baseline framework for video-based 2D/3D human pose estimation that can achieve 10 times efficiency improvement over existing works without any performance degradation, named DeciWatch. Unlike current solutions that estimate each frame in a video, DeciWatch introduces a simple yet effective sample-denoise-recover framework that only watches sparsely sampled frames, taking advantage of the continuity of human motions and the lightweight pose representation. Specifically, DeciWatch uniformly samples less than 10% video frames for detailed estimation, denoises the estimated 2D/3D poses with an efficient Transformer architecture, and then accurately recovers the rest of the frames using another Transformer-based network. Comprehensive experimental results on three video-based human pose estimation and body mesh recovery tasks with four datasets validate the efficiency and effectiveness of DeciWatch. Code is available at https://github.com/cure-lab/DeciWatch.","url_abs":"https://arxiv.org/abs/2203.08713v2","url_pdf":"https://arxiv.org/pdf/2203.08713v2.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":"deciwatch-a-simple-baseline-for-10x-efficient","repo_url":"https://github.com/cure-lab/DeciWatch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"2d-human-pose-estimation","task_name":"2D Human Pose Estimation"},{"task_slug":"3d-human-pose-estimation","task_name":"3D Human Pose Estimation"},{"task_slug":"3d-pose-estimation","task_name":"3D Pose Estimation"},{"task_slug":"3d-shape-reconstruction-from-videos","task_name":"3D Shape Reconstruction from Videos"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/2d-human-pose-estimation-on-jhmdb-2d-poses","task":"2D Human Pose Estimation","dataset":"JHMDB (2D poses only)","model":"DeciWatch","rank_in_archive_order":1,"of":5,"metrics":{"PCK":"98.8"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-3dpw","task":"3D Human Pose Estimation","dataset":"3DPW","model":"DeciWatch-PARE","rank_in_archive_order":70,"of":119,"metrics":{"MPJPE":"75.5","PA-MPJPE":"46.4"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-aist","task":"3D Human Pose Estimation","dataset":"AIST++","model":"DeciWatch","rank_in_archive_order":4,"of":5,"metrics":{"MPJPE":"67.2","Single-view":"Y"},"uses_additional_data":false},{"leaderboard":"/sota/pose-estimation-on-j-hmdb","task":"Pose Estimation","dataset":"J-HMDB","model":"DeciWatch","rank_in_archive_order":2,"of":5,"metrics":{"Mean PCK@0.05":"80.6","Mean PCK@0.1":"94.6","Mean PCK@0.2":"99.0"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2203.08713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.08713"}},"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/cure-lab/DeciWatch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":7},"by_repo_kind":{"official":{"samples":8,"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":0,"samples":[{"code_sha256_prefix":"34067eef72357f72","entry":"qrot","repo":"cure-lab/DeciWatch","repo_kind":"official","path":"lib/utils/cam_utils.py","file_url":"https://github.com/cure-lab/DeciWatch/blob/HEAD/lib/utils/cam_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"34067eef72357f72"}},{"code_sha256_prefix":"1a2906773e636ce9","entry":"batch_compute_similarity_transform_torch","repo":"cure-lab/DeciWatch","repo_kind":"official","path":"lib/utils/eval_metrics.py","file_url":"https://github.com/cure-lab/DeciWatch/blob/HEAD/lib/utils/eval_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1a2906773e636ce9"}},{"code_sha256_prefix":"5c5604eb9db2dc11","entry":"build_model","repo":"cure-lab/DeciWatch","repo_kind":"official","path":"lib/models/deciwatch.py","file_url":"https://github.com/cure-lab/DeciWatch/blob/HEAD/lib/models/deciwatch.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5c5604eb9db2dc11"}},{"code_sha256_prefix":"c49c4d20e89f777f","entry":"calculate_mpjpe","repo":"cure-lab/DeciWatch","repo_kind":"official","path":"lib/utils/eval_metrics.py","file_url":"https://github.com/cure-lab/DeciWatch/blob/HEAD/lib/utils/eval_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c49c4d20e89f777f"}},{"code_sha256_prefix":"bfb5bcc5d76b73d1","entry":"compute_error_accel","repo":"cure-lab/DeciWatch","repo_kind":"official","path":"lib/utils/eval_metrics.py","file_url":"https://github.com/cure-lab/DeciWatch/blob/HEAD/lib/utils/eval_metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bfb5bcc5d76b73d1"}},{"code_sha256_prefix":"2c8338c89fe8975c","entry":"image_coordinates","repo":"cure-lab/DeciWatch","repo_kind":"official","path":"lib/utils/cam_utils.py","file_url":"https://github.com/cure-lab/DeciWatch/blob/HEAD/lib/utils/cam_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2c8338c89fe8975c"}},{"code_sha256_prefix":"e53a897a491c4627","entry":"normalize_screen_coordinates","repo":"cure-lab/DeciWatch","repo_kind":"official","path":"lib/utils/cam_utils.py","file_url":"https://github.com/cure-lab/DeciWatch/blob/HEAD/lib/utils/cam_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e53a897a491c4627"}},{"code_sha256_prefix":"f0ba038b51ec3afb","entry":"update_cfg","repo":"cure-lab/DeciWatch","repo_kind":"official","path":"lib/core/config.py","file_url":"https://github.com/cure-lab/DeciWatch/blob/HEAD/lib/core/config.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f0ba038b51ec3afb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}