{"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/tokenhmr-advancing-human-mesh-recovery-with-a","title":"TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation","arxiv_id":"2404.16752","date":"2024-04-25","proceeding":"CVPR 2024 1","authors":["Sai Kumar Dwivedi","Yu Sun","Priyanka Patel","Yao Feng","Michael J. Black"],"abstract":"We address the problem of regressing 3D human pose and shape from a single image, with a focus on 3D accuracy. The current best methods leverage large datasets of 3D pseudo-ground-truth (p-GT) and 2D keypoints, leading to robust performance. With such methods, we observe a paradoxical decline in 3D pose accuracy with increasing 2D accuracy. This is caused by biases in the p-GT and the use of an approximate camera projection model. We quantify the error induced by current camera models and show that fitting 2D keypoints and p-GT accurately causes incorrect 3D poses. Our analysis defines the invalid distances within which minimizing 2D and p-GT losses is detrimental. We use this to formulate a new loss Threshold-Adaptive Loss Scaling (TALS) that penalizes gross 2D and p-GT losses but not smaller ones. With such a loss, there are many 3D poses that could equally explain the 2D evidence. To reduce this ambiguity we need a prior over valid human poses but such priors can introduce unwanted bias. To address this, we exploit a tokenized representation of human pose and reformulate the problem as token prediction. This restricts the estimated poses to the space of valid poses, effectively providing a uniform prior. Extensive experiments on the EMDB and 3DPW datasets show that our reformulated keypoint loss and tokenization allows us to train on in-the-wild data while improving 3D accuracy over the state-of-the-art. Our models and code are available for research at https://tokenhmr.is.tue.mpg.de.","url_abs":"https://arxiv.org/abs/2404.16752v1","url_pdf":"https://arxiv.org/pdf/2404.16752v1.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":"tokenhmr-advancing-human-mesh-recovery-with-a","repo_url":"https://github.com/saidwivedi/TokenHMR","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":"human-mesh-recovery","task_name":"Human Mesh Recovery"},{"task_slug":null,"task_name":"valid"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-human-pose-estimation-on-3dpw","task":"3D Human Pose Estimation","dataset":"3DPW","model":"TokenHMR (SD + ITW + BL)","rank_in_archive_order":29,"of":119,"metrics":{"MPJPE":"71","MPVPE":"84.6","PA-MPJPE":"44.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.16752","atlas_url":"https://app.syntology.ai/?focus=2404.16752","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}