{"ID":2843489,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.08387","arxiv_id":"2511.08387","title":"RAPTR: Radar-based 3D Pose Estimation using Transformer","abstract":"Radar-based indoor 3D human pose estimation typically relied on fine-grained 3D keypoint labels, which are costly to obtain especially in complex indoor settings involving clutter, occlusions, or multiple people. In this paper, we propose \\textbf{RAPTR} (RAdar Pose esTimation using tRansformer) under weak supervision, using only 3D BBox and 2D keypoint labels which are considerably easier and more scalable to collect. Our RAPTR is characterized by a two-stage pose decoder architecture with a pseudo-3D deformable attention to enhance (pose/joint) queries with multi-view radar features: a pose decoder estimates initial 3D poses with a 3D template loss designed to utilize the 3D BBox labels and mitigate depth ambiguities; and a joint decoder refines the initial poses with 2D keypoint labels and a 3D gravity loss. Evaluated on two indoor radar datasets, RAPTR outperforms existing methods, reducing joint position error by $34.3\\%$ on HIBER and $76.9\\%$ on MMVR. Our implementation is available at https://github.com/merlresearch/radar-pose-transformer.","short_abstract":"Radar-based indoor 3D human pose estimation typically relied on fine-grained 3D keypoint labels, which are costly to obtain especially in complex indoor settings involving clutter, occlusions, or multiple people. In this paper, we propose \\textbf{RAPTR} (RAdar Pose esTimation using tRansformer) under weak supervision,...","url_abs":"https://arxiv.org/abs/2511.08387","url_pdf":"https://arxiv.org/pdf/2511.08387v1","authors":"[\"Sorachi Kato\",\"Ryoma Yataka\",\"Pu Perry Wang\",\"Pedro Miraldo\",\"Takuya Fujihashi\",\"Petros Boufounos\"]","published":"2025-11-11T16:07:49Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"eess.SP\"]","methods":"[\"Transformer\"]","has_code":false,"code_links":[{"ID":607219,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2843489,"paper_url":"https://arxiv.org/abs/2511.08387","paper_title":"RAPTR: Radar-based 3D Pose Estimation using Transformer","repo_url":"https://github.com/merlresearch/radar-pose-transformer","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}