{"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/lightweight-multi-view-3d-pose-estimation","title":"Lightweight Multi-View 3D Pose Estimation through Camera-Disentangled Representation","arxiv_id":"2004.02186","date":"2020-04-05","proceeding":"CVPR 2020 6","authors":["Edoardo Remelli","Shangchen Han","Sina Honari","Pascal Fua","Robert Wang"],"abstract":"We present a lightweight solution to recover 3D pose from multi-view images captured with spatially calibrated cameras. Building upon recent advances in interpretable representation learning, we exploit 3D geometry to fuse input images into a unified latent representation of pose, which is disentangled from camera view-points. This allows us to reason effectively about 3D pose across different views without using compute-intensive volumetric grids. Our architecture then conditions the learned representation on camera projection operators to produce accurate per-view 2d detections, that can be simply lifted to 3D via a differentiable Direct Linear Transform (DLT) layer. In order to do it efficiently, we propose a novel implementation of DLT that is orders of magnitude faster on GPU architectures than standard SVD-based triangulation methods. We evaluate our approach on two large-scale human pose datasets (H36M and Total Capture): our method outperforms or performs comparably to the state-of-the-art volumetric methods, while, unlike them, yielding real-time performance.","url_abs":"https://arxiv.org/abs/2004.02186v2","url_pdf":"https://arxiv.org/pdf/2004.02186v2.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":[],"tasks":[{"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-geometry","task_name":"3D geometry"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-human36m","task":"3D Human Pose Estimation","dataset":"Human3.6M","model":"LWCDR","rank_in_archive_order":8,"of":88,"metrics":{"Average MPJPE (mm)":"30.2","Multi-View or Monocular":"Multi-View","Using 2D ground-truth joints":"No"},"uses_additional_data":false},{"leaderboard":"/sota/3d-human-pose-estimation-on-total-capture","task":"3D Human Pose Estimation","dataset":"Total Capture","model":"LWCDR","rank_in_archive_order":4,"of":14,"metrics":{"Average MPJPE (mm)":"27.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.02186","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}