{"ID":2858943,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.07313","arxiv_id":"2510.07313","title":"WristWorld: Generating Wrist-Views via 4D World Models for Robotic Manipulation","abstract":"Wrist-view observations are crucial for VLA models as they capture fine-grained hand-object interactions that directly enhance manipulation performance. Yet large-scale datasets rarely include such recordings, resulting in a substantial gap between abundant anchor views and scarce wrist views. Existing world models cannot bridge this gap, as they require a wrist-view first frame and thus fail to generate wrist-view videos from anchor views alone. Amid this gap, recent visual geometry models such as VGGT emerge with geometric and cross-view priors that make it possible to address extreme viewpoint shifts. Inspired by these insights, we propose WristWorld, the first 4D world model that generates wrist-view videos solely from anchor views. WristWorld operates in two stages: (i) Reconstruction, which extends VGGT and incorporates our Spatial Projection Consistency (SPC) Loss to estimate geometrically consistent wrist-view poses and 4D point clouds; (ii) Generation, which employs our video generation model to synthesize temporally coherent wrist-view videos from the reconstructed perspective. Experiments on Droid, Calvin, and Franka Panda demonstrate state-of-the-art video generation with superior spatial consistency, while also improving VLA performance, raising the average task completion length on Calvin by 3.81% and closing 42.4% of the anchor-wrist view gap.","short_abstract":"Wrist-view observations are crucial for VLA models as they capture fine-grained hand-object interactions that directly enhance manipulation performance. Yet large-scale datasets rarely include such recordings, resulting in a substantial gap between abundant anchor views and scarce wrist views. Existing world models can...","url_abs":"https://arxiv.org/abs/2510.07313","url_pdf":"https://arxiv.org/pdf/2510.07313v1","authors":"[\"Zezhong Qian\",\"Xiaowei Chi\",\"Yuming Li\",\"Shizun Wang\",\"Zhiyuan Qin\",\"Xiaozhu Ju\",\"Sirui Han\",\"Shanghang Zhang\"]","published":"2025-10-08T17:59:08Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.RO\"]","methods":"[]","has_code":false}