{"ID":5936922,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T17:51:18.37832961Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.05390","arxiv_id":"2607.05390","title":"Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models","abstract":"Predicting object dynamics (i.e., world modeling) is a fundamental challenge for robotic manipulation, and modeling deformable objects presents a particularly difficult case due to their high-dimensional state spaces and complex material properties. While current world models approach this through two distinct paradigms: learning the dynamics over the 2D pixel space or more explicit 3D geometric space. A systematic understanding of their relative strengths and limitations remains elusive due to the lack of diverse, large-scale real-world data. To address this, we present Deform360, a large-scale visuotactile dataset featuring 198 daily-life objects, 1,980 interaction sequences, and over 215 hours of observations from 41 surround-view cameras and bimanual tactile grippers to capture both global motion and contact-induced local deformations. Leveraging a novel markerless visuotactile 3D tracking pipeline to extract dense geometry and motion, we systematically evaluate current state-of-the-art world models, comparing 2D video models against 3D particle models. Finally, we provide a preliminary demonstration indicating the real-world applicability of our dataset by performing robot planning tasks on deformable objects. Our analysis reveals key insights into the trade-offs between structural priors and scalability, providing a solid benchmark for future research in generalizable deformable object-centric world modeling. Project website: https://deform360.lhy.xyz","short_abstract":"Predicting object dynamics (i.e., world modeling) is a fundamental challenge for robotic manipulation, and modeling deformable objects presents a particularly difficult case due to their high-dimensional state spaces and complex material properties. While current world models approach this through two distinct paradigm...","url_abs":"https://arxiv.org/abs/2607.05390","url_pdf":"https://arxiv.org/pdf/2607.05390v1","authors":"[\"Hongyu Li\",\"Wanjia Fu\",\"Xiaoyan Cong\",\"Zekun Li\",\"Binghao Huang\",\"Hanxiao Jiang\",\"Xintong He\",\"Yiqing Liang\",\"Rao Fu\",\"Tao Lu\",\"Srinath Sridhar\",\"Kevin A. Smith\",\"George Konidaris\",\"Yunzhu Li\"]","published":"2026-07-06T17:59:18Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.CV\"]","methods":"[]","project_urls":"[\"https://deform360.lhy.xyz\"]","has_code":false,"code_links":[{"ID":613942,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-07T03:14:33.014478982Z","DeletedAt":null,"paper_id":5936922,"paper_url":"https://arxiv.org/abs/2607.05390","paper_title":"Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models","repo_url":"https://github.com/lhy0807/deform360","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}