{"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-x-hybrid-analytical-neural-inverse","title":"HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery","arxiv_id":"2304.05690","date":"2023-04-12","proceeding":null,"authors":["Jiefeng Li","Siyuan Bian","Chao Xu","Zhicun Chen","Lixin Yang","Cewu Lu"],"abstract":"Recovering whole-body mesh by inferring the abstract pose and shape parameters from visual content can obtain 3D bodies with realistic structures. However, the inferring process is highly non-linear and suffers from image-mesh misalignment, resulting in inaccurate reconstruction. In contrast, 3D keypoint estimation methods utilize the volumetric representation to achieve pixel-level accuracy but may predict unrealistic body structures. To address these issues, this paper presents a novel hybrid inverse kinematics solution, HybrIK, that integrates the merits of 3D keypoint estimation and body mesh recovery in a unified framework. HybrIK directly transforms accurate 3D joints to body-part rotations via twist-and-swing decomposition. The swing rotations are analytically solved with 3D joints, while the twist rotations are derived from visual cues through neural networks. To capture comprehensive whole-body details, we further develop a holistic framework, HybrIK-X, which enhances HybrIK with articulated hands and an expressive face. HybrIK-X is fast and accurate by solving the whole-body pose with a one-stage model. Experiments demonstrate that HybrIK and HybrIK-X preserve both the accuracy of 3D joints and the realistic structure of the parametric human model, leading to pixel-aligned whole-body mesh recovery. The proposed method significantly surpasses the state-of-the-art methods on various benchmarks for body-only, hand-only, and whole-body scenarios. Code and results can be found at https://jeffli.site/HybrIK-X/","url_abs":"https://arxiv.org/abs/2304.05690v1","url_pdf":"https://arxiv.org/pdf/2304.05690v1.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-x-hybrid-analytical-neural-inverse","repo_url":"https://github.com/Jeff-sjtu/HybrIK","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"hybrik-x-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-reconstruction","task_name":"3D Human Reconstruction"},{"task_slug":"keypoint-estimation","task_name":"Keypoint Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-3dpw","task":"3D Human Pose Estimation","dataset":"3DPW","model":"HybrIK (HRNet-W48)","rank_in_archive_order":24,"of":119,"metrics":{"MPJPE":"71.6","MPVPE":"82.3","PA-MPJPE":"41.8"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-agora","task":"3D Human Pose Estimation","dataset":"AGORA","model":"HybrIK-X","rank_in_archive_order":3,"of":11,"metrics":{"B-MPJPE":"67.2","B-MVE":"68.5","B-NMJE":"72.3","B-NMVE":"73.7"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-agora","task":"3D Human Pose Estimation","dataset":"AGORA","model":"HybrIK","rank_in_archive_order":4,"of":11,"metrics":{"B-MPJPE":"77","B-MVE":"73.9","B-NMJE":"84.6","B-NMVE":"81.2"},"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 (HRNet-W48)","rank_in_archive_order":46,"of":108,"metrics":{"AUC":"47.3","MPJPE":"91","PCK":"87.1"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-reconstruction-on-agora-1","task":"3D Human Reconstruction","dataset":"AGORA","model":"HybrIK-X","rank_in_archive_order":1,"of":5,"metrics":{"FB-MPJPE":"107.6","FB-MVE":"112.1","FB-NMJE":"115.7","FB-NMVE":"120.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.05690","atlas_url":"https://app.syntology.ai/?focus=2304.05690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05690"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/jeffffffli/HybrIK","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Jeff-sjtu/HybrIK","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":8},"by_repo_kind":{"listed":{"samples":8,"ran":0,"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":"fabada0c3f6b8840","entry":"flip","repo":"Jeff-sjtu/HybrIK","repo_kind":"listed","path":"hybrik/models/HRNetSMPLXCamKid.py","file_url":"https://github.com/Jeff-sjtu/HybrIK/blob/HEAD/hybrik/models/HRNetSMPLXCamKid.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":"fabada0c3f6b8840"}},{"code_sha256_prefix":"ed832a8183efcc97","entry":"focalLength_mm2px","repo":"Jeff-sjtu/HybrIK","repo_kind":"listed","path":"hybrik/datasets/agora_smplx.py","file_url":"https://github.com/Jeff-sjtu/HybrIK/blob/HEAD/hybrik/datasets/agora_smplx.py","link_basis":"harvester_set","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":"ed832a8183efcc97"}},{"code_sha256_prefix":"733d8811b481fdbe","entry":"get_focal","repo":"Jeff-sjtu/HybrIK","repo_kind":"listed","path":"hybrik/datasets/agora_smplx.py","file_url":"https://github.com/Jeff-sjtu/HybrIK/blob/HEAD/hybrik/datasets/agora_smplx.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":"733d8811b481fdbe"}},{"code_sha256_prefix":"0635936243f338d5","entry":"norm_heatmap","repo":"Jeff-sjtu/HybrIK","repo_kind":"listed","path":"hybrik/models/HRNetSMPLXCamKid.py","file_url":"https://github.com/Jeff-sjtu/HybrIK/blob/HEAD/hybrik/models/HRNetSMPLXCamKid.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":"0635936243f338d5"}},{"code_sha256_prefix":"a828d7ddc0f76aac","entry":"norm_heatmap","repo":"Jeff-sjtu/HybrIK","repo_kind":"listed","path":"hybrik/models/simple3dposeBaseSMPL.py","file_url":"https://github.com/Jeff-sjtu/HybrIK/blob/HEAD/hybrik/models/simple3dposeBaseSMPL.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":"a828d7ddc0f76aac"}},{"code_sha256_prefix":"8cc86609ecbd6234","entry":"project","repo":"Jeff-sjtu/HybrIK","repo_kind":"listed","path":"hybrik/datasets/agora_smplx.py","file_url":"https://github.com/Jeff-sjtu/HybrIK/blob/HEAD/hybrik/datasets/agora_smplx.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":"8cc86609ecbd6234"}},{"code_sha256_prefix":"3b94245b39283e5c","entry":"weighted_l1_loss","repo":"Jeff-sjtu/HybrIK","repo_kind":"listed","path":"hybrik/models/criterion.py","file_url":"https://github.com/Jeff-sjtu/HybrIK/blob/HEAD/hybrik/models/criterion.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":"3b94245b39283e5c"}},{"code_sha256_prefix":"86dec2a5c79f02f6","entry":"weighted_laplace_loss","repo":"Jeff-sjtu/HybrIK","repo_kind":"listed","path":"hybrik/models/criterion.py","file_url":"https://github.com/Jeff-sjtu/HybrIK/blob/HEAD/hybrik/models/criterion.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":"86dec2a5c79f02f6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}