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.

翻译：我们提出了ReCamDriving，一种纯视觉的、相机控制的新轨迹视频生成框架。基于修复的方法无法恢复复杂的伪影，而基于LiDAR的方法依赖于稀疏且不完整的线索，与此不同，ReCamDriving利用密集且场景完整的3DGS渲染提供显式几何引导，实现了精确的相机可控生成。为了缓解在3DGS渲染条件下对修复行为的过拟合，ReCamDriving采用了两阶段训练范式：第一阶段使用相机位姿进行粗略控制，第二阶段则引入3DGS渲染以提供细粒度的视点和几何引导。此外，我们提出了一种基于3DGS的跨轨迹数据构建策略，以消除相机变换模式在训练与测试之间的差距，从而能够从单目视频中获得可扩展的多轨迹监督。基于此策略，我们构建了ParaDrive数据集，其中包含超过11万个平行轨迹视频对。大量实验表明，ReCamDriving在相机可控性和结构一致性方面达到了最先进的水平。