{"ID":2855525,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.24734","arxiv_id":"2510.24734","title":"DrivingScene: A Multi-Task Online Feed-Forward 3D Gaussian Splatting Method for Dynamic Driving Scenes","abstract":"Real-time, high-fidelity reconstruction of dynamic driving scenes is challenged by complex dynamics and sparse views, with prior methods struggling to balance quality and efficiency. We propose DrivingScene, an online, feed-forward framework that reconstructs 4D dynamic scenes from only two consecutive surround-view images. Our key innovation is a lightweight residual flow network that predicts the non-rigid motion of dynamic objects per camera on top of a learned static scene prior, explicitly modeling dynamics via scene flow. We also introduce a coarse-to-fine training paradigm that circumvents the instabilities common to end-to-end approaches. Experiments on nuScenes dataset show our image-only method simultaneously generates high-quality depth, scene flow, and 3D Gaussian point clouds online, significantly outperforming state-of-the-art methods in both dynamic reconstruction and novel view synthesis.","short_abstract":"Real-time, high-fidelity reconstruction of dynamic driving scenes is challenged by complex dynamics and sparse views, with prior methods struggling to balance quality and efficiency. We propose DrivingScene, an online, feed-forward framework that reconstructs 4D dynamic scenes from only two consecutive surround-view im...","url_abs":"https://arxiv.org/abs/2510.24734","url_pdf":"https://arxiv.org/pdf/2510.24734v1","authors":"[\"Qirui Hou\",\"Wenzhang Sun\",\"Chang Zeng\",\"Chunfeng Wang\",\"Hao Li\",\"Jianxun Cui\"]","published":"2025-10-14T03:32:46Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\",\"cs.RO\"]","methods":"[]","has_code":false}