{"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/hybrik-a-hybrid-analytical-neural-inverse","title":"HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation","arxiv_id":"2011.14672","date":"2020-11-30","proceeding":"CVPR 2021 1","authors":["Jiefeng Li","Chao Xu","Zhicun Chen","Siyuan Bian","Lixin Yang","Cewu Lu"],"abstract":"Model-based 3D pose and shape estimation methods reconstruct a full 3D mesh for the human body by estimating several parameters. However, learning the abstract parameters is a highly non-linear process and suffers from image-model misalignment, leading to mediocre model performance. In contrast, 3D keypoint estimation methods combine deep CNN network with the volumetric representation to achieve pixel-level localization accuracy but may predict unrealistic body structure. In this paper, we address the above issues by bridging the gap between body mesh estimation and 3D keypoint estimation. We propose a novel hybrid inverse kinematics solution (HybrIK). HybrIK directly transforms accurate 3D joints to relative body-part rotations for 3D body mesh reconstruction, via the twist-and-swing decomposition. The swing rotation is analytically solved with 3D joints, and the twist rotation is derived from the visual cues through the neural network. We show that HybrIK preserves both the accuracy of 3D pose and the realistic body structure of the parametric human model, leading to a pixel-aligned 3D body mesh and a more accurate 3D pose than the pure 3D keypoint estimation methods. Without bells and whistles, the proposed method surpasses the state-of-the-art methods by a large margin on various 3D human pose and shape benchmarks. As an illustrative example, HybrIK outperforms all the previous methods by 13.2 mm MPJPE and 21.9 mm PVE on 3DPW dataset. Our code is available at https://github.com/Jeff-sjtu/HybrIK.","url_abs":"https://arxiv.org/abs/2011.14672v4","url_pdf":"https://arxiv.org/pdf/2011.14672v4.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":"hybrik-a-hybrid-analytical-neural-inverse","repo_url":"https://github.com/Jeff-sjtu/HybrIK","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hybrik-a-hybrid-analytical-neural-inverse","repo_url":"https://github.com/jeff-sjtu/dnd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"hybrik-a-hybrid-analytical-neural-inverse","repo_url":"https://github.com/jeff-sjtu/niki","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"hybrik-a-hybrid-analytical-neural-inverse","repo_url":"https://github.com/jeffffffli/HybrIK","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":"3d-human-pose-and-shape-estimation","task_name":"3D human pose and shape estimation"},{"task_slug":"keypoint-estimation","task_name":"Keypoint 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":"HybrIK","rank_in_archive_order":30,"of":119,"metrics":{"MPJPE":"74.1","MPVPE":"86.5","PA-MPJPE":"45.0"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-emdb","task":"3D Human Pose Estimation","dataset":"EMDB","model":"HybrIK","rank_in_archive_order":5,"of":13,"metrics":{"Average MPJAE (deg)":"24.5174","Average MPJAE-PA (deg)":"23.0704","Average MPJPE (mm)":"103.037","Average MPJPE-PA (mm)":"65.5935","Average MVE (mm)":"122.193","Average MVE-PA (mm)":"80.3678","Jitter (10m/s^3)":"49.2068"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-mpi-inf-3dhp","task":"3D Human Pose Estimation","dataset":"MPI-INF-3DHP","model":"HybrIK","rank_in_archive_order":47,"of":108,"metrics":{"AUC":"46.9","MPJPE":"91.0","PCK":"87.5"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2011.14672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.14672"}},"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/jeff-sjtu/dnd","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jeffffffli/HybrIK","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Jeff-sjtu/HybrIK","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jeff-sjtu/niki","reach":{"status":"unanswered"}}],"summary":{"ran_violates":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":0,"samples":[{"code_sha256_prefix":"77eed234a0291c47","entry":"xyxy2xywh","repo":"jeffffffli/HybrIK","repo_kind":"listed","path":"scripts/demo_image.py","file_url":"https://github.com/jeffffffli/HybrIK/blob/HEAD/scripts/demo_image.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":"77eed234a0291c47"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}