{"ID":2833415,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.03621","arxiv_id":"2512.03621","title":"ReCamDriving: LiDAR-Free Camera-Controlled Novel Trajectory Video Generation","abstract":"We propose ReCamDriving, a purely vision-based, camera-controlled novel-trajectory video generation framework. While repair-based methods fail to restore complex artifacts and LiDAR-based approaches rely on sparse and incomplete cues, ReCamDriving leverages dense and scene-complete 3DGS renderings for explicit geometric guidance, achieving precise camera-controllable generation. To mitigate overfitting to restoration behaviors when conditioned on 3DGS renderings, ReCamDriving adopts a two-stage training paradigm: the first stage uses camera poses for coarse control, while the second stage incorporates 3DGS renderings for fine-grained viewpoint and geometric guidance. Furthermore, we present a 3DGS-based cross-trajectory data curation strategy to eliminate the train-test gap in camera transformation patterns, enabling scalable multi-trajectory supervision from monocular videos. Based on this strategy, we construct the ParaDrive dataset, containing over 110K parallel-trajectory video pairs. Extensive experiments demonstrate that ReCamDriving achieves state-of-the-art camera controllability and structural consistency.","short_abstract":"We propose ReCamDriving, a purely vision-based, camera-controlled novel-trajectory video generation framework. While repair-based methods fail to restore complex artifacts and LiDAR-based approaches rely on sparse and incomplete cues, ReCamDriving leverages dense and scene-complete 3DGS renderings for explicit geometri...","url_abs":"https://arxiv.org/abs/2512.03621","url_pdf":"https://arxiv.org/pdf/2512.03621v2","authors":"[\"Yaokun Li\",\"Shuaixian Wang\",\"Mantang Guo\",\"Jiehui Huang\",\"Taojun Ding\",\"Mu Hu\",\"Kaixuan Wang\",\"Shaojie Shen\",\"Guang Tan\"]","published":"2025-12-03T09:55:25Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}