{"ID":2881584,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.11898","arxiv_id":"2508.11898","title":"OmniD: Generalizable Robot Manipulation Policy via Image-Based BEV Representation","abstract":"The visuomotor policy can easily overfit to its training datasets, such as fixed camera positions and backgrounds. This overfitting makes the policy perform well in the in-distribution scenarios but underperform in the out-of-distribution generalization. Additionally, the existing methods also have difficulty fusing multi-view information to generate an effective 3D representation. To tackle these issues, we propose Omni-Vision Diffusion Policy (OmniD), a multi-view fusion framework that synthesizes image observations into a unified bird's-eye view (BEV) representation. We introduce a deformable attention-based Omni-Feature Generator (OFG) to selectively abstract task-relevant features while suppressing view-specific noise and background distractions. OmniD achieves 11\\%, 17\\%, and 84\\% average improvement over the best baseline model for in-distribution, out-of-distribution, and few-shot experiments, respectively. Training code and simulation benchmark are available: https://github.com/1mather/omnid.git","short_abstract":"The visuomotor policy can easily overfit to its training datasets, such as fixed camera positions and backgrounds. This overfitting makes the policy perform well in the in-distribution scenarios but underperform in the out-of-distribution generalization. Additionally, the existing methods also have difficulty fusing mu...","url_abs":"https://arxiv.org/abs/2508.11898","url_pdf":"https://arxiv.org/pdf/2508.11898v1","authors":"[\"Jilei Mao\",\"Jiarui Guan\",\"Yingjuan Tang\",\"Qirui Hu\",\"Zhihang Li\",\"Junjie Yu\",\"Yongjie Mao\",\"Yunzhe Sun\",\"Shuang Liu\",\"Xiaozhu Ju\"]","published":"2025-08-16T04:02:53Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":610825,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2881584,"paper_url":"https://arxiv.org/abs/2508.11898","paper_title":"OmniD: Generalizable Robot Manipulation Policy via Image-Based BEV Representation","repo_url":"https://github.com/1mather/omnid.git","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}