{"ID":2838536,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.17116","arxiv_id":"2511.17116","title":"PEGS: Physics-Event Enhanced Large Spatiotemporal Motion Reconstruction via 3D Gaussian Splatting","abstract":"Reconstruction of rigid motion over large spatiotemporal scales remains a challenging task due to limitations in modeling paradigms, severe motion blur, and insufficient physical consistency. In this work, we propose PEGS, a framework that integrates Physical priors with Event stream enhancement within a 3D Gaussian Splatting pipeline to perform deblurred target-focused modeling and motion recovery. We introduce a cohesive triple-level supervision scheme that enforces physical plausibility via an acceleration constraint, leverages event streams for high-temporal resolution guidance, and employs a Kalman regularizer to fuse multi-source observations. Furthermore, we design a motion-aware simulated annealing strategy that adaptively schedules the training process based on real-time kinematic states. We also contribute the first RGB-Event paired dataset targeting natural, fast rigid motion across diverse scenarios. Experiments show PEGS's superior performance in reconstructing motion over large spatiotemporal scales compared to mainstream dynamic methods.","short_abstract":"Reconstruction of rigid motion over large spatiotemporal scales remains a challenging task due to limitations in modeling paradigms, severe motion blur, and insufficient physical consistency. In this work, we propose PEGS, a framework that integrates Physical priors with Event stream enhancement within a 3D Gaussian Sp...","url_abs":"https://arxiv.org/abs/2511.17116","url_pdf":"https://arxiv.org/pdf/2511.17116v1","authors":"[\"Yijun Xu\",\"Jingrui Zhang\",\"Hongyi Liu\",\"Yuhan Chen\",\"Yuanyang Wang\",\"Qingyao Guo\",\"Dingwen Wang\",\"Lei Yu\",\"Chu He\"]","published":"2025-11-21T10:27:51Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}