{"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/humans-in-4d-reconstructing-and-tracking","title":"Humans in 4D: Reconstructing and Tracking Humans with Transformers","arxiv_id":"2305.20091","date":"2023-05-31","proceeding":"ICCV 2023 1","authors":["Shubham Goel","Georgios Pavlakos","Jathushan Rajasegaran","Angjoo Kanazawa","Jitendra Malik"],"abstract":"We present an approach to reconstruct humans and track them over time. At the core of our approach, we propose a fully \"transformerized\" version of a network for human mesh recovery. This network, HMR 2.0, advances the state of the art and shows the capability to analyze unusual poses that have in the past been difficult to reconstruct from single images. To analyze video, we use 3D reconstructions from HMR 2.0 as input to a tracking system that operates in 3D. This enables us to deal with multiple people and maintain identities through occlusion events. Our complete approach, 4DHumans, achieves state-of-the-art results for tracking people from monocular video. Furthermore, we demonstrate the effectiveness of HMR 2.0 on the downstream task of action recognition, achieving significant improvements over previous pose-based action recognition approaches. Our code and models are available on the project website: https://shubham-goel.github.io/4dhumans/.","url_abs":"https://arxiv.org/abs/2305.20091v3","url_pdf":"https://arxiv.org/pdf/2305.20091v3.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":"humans-in-4d-reconstructing-and-tracking","repo_url":"https://github.com/shubham-goel/4D-Humans","is_official":1,"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":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"human-mesh-recovery","task_name":"Human Mesh Recovery"},{"task_slug":"pose-tracking","task_name":"Pose Tracking"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"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":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-3dpw","task":"3D Human Pose Estimation","dataset":"3DPW","model":"HMR 2.0","rank_in_archive_order":23,"of":119,"metrics":{"MPJPE":"69.8","MPVPE":"82.2","PA-MPJPE":"44.4"},"uses_additional_data":false},{"leaderboard":"/sota/pose-tracking-on-posetrack2018","task":"Pose Tracking","dataset":"PoseTrack2018","model":"4DHumans + ViTDet","rank_in_archive_order":3,"of":5,"metrics":{"IDF1":"79.3","IDs":"367","MOTA":"61.9"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.20091","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.20091"}},"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/shubham-goel/4D-Humans","reach":null}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":"044509f32558dfd9","entry":"Discriminator","repo":"shubham-goel/4D-Humans","repo_kind":"official","path":"hmr2/models/hmr2.py","file_url":"https://github.com/shubham-goel/4D-Humans/blob/HEAD/hmr2/models/hmr2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"044509f32558dfd9"}},{"code_sha256_prefix":"a2086bce04d065c0","entry":"Keypoint2DLoss","repo":"shubham-goel/4D-Humans","repo_kind":"official","path":"hmr2/models/hmr2.py","file_url":"https://github.com/shubham-goel/4D-Humans/blob/HEAD/hmr2/models/hmr2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a2086bce04d065c0"}},{"code_sha256_prefix":"b0ad64515a64338e","entry":"Keypoint3DLoss","repo":"shubham-goel/4D-Humans","repo_kind":"official","path":"hmr2/models/hmr2.py","file_url":"https://github.com/shubham-goel/4D-Humans/blob/HEAD/hmr2/models/hmr2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b0ad64515a64338e"}},{"code_sha256_prefix":"8afa0da053f74850","entry":"ParameterLoss","repo":"shubham-goel/4D-Humans","repo_kind":"official","path":"hmr2/models/hmr2.py","file_url":"https://github.com/shubham-goel/4D-Humans/blob/HEAD/hmr2/models/hmr2.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8afa0da053f74850"}},{"code_sha256_prefix":"c3db9cdd4369c570","entry":"HMR2","repo":"shubham-goel/4D-Humans","repo_kind":"official","path":"hmr2/models/hmr2.py","file_url":"https://github.com/shubham-goel/4D-Humans/blob/HEAD/hmr2/models/hmr2.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":"c3db9cdd4369c570"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}