ReCamDriving: LiDAR-Free Camera-Controlled Novel Trajectory Video Generation

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.

Comparison of novel-trajectory generation. Repair-based methods (e.g., Difix3D+) suffer from severe artifacts under novel viewpoints, while LiDAR-based camera-controlled methods (e.g., StreetCrafter) show geometric inconsistencies in occluded or distant regions due to incomplete cues. In contrast, ReCamDriving employs a coarse-to-fine two-stage training strategy that leverages dense scene-structure information from novel-trajectory 3DGS renderings for precise camera control and structurally consistent generation.

Based on our data curation strategy, we constructed the ParaDrive dataset, which contains over 110K parallel-trajectory video pairs, enabling scalable multi-trajectory supervision.

We are finalizing the release of the code and data and aim to complete it as soon as possible. Please stay tuned!

• Paper released on arXiv.
• Release training and inference code.
• Release model weights.
• Release ParaDrive dataset.

If you find our work helpful, please consider citing:

@misc{li2025recamdrivinglidarfreecameracontrollednovel,
      title={ReCamDriving: LiDAR-Free Camera-Controlled Novel Trajectory Video Generation}, 
      author={Yaokun Li and Shuaixian Wang and Mantang Guo and Jiehui Huang and Taojun Ding and Mu Hu and Kaixuan Wang and Shaojie Shen and Guang Tan},
      year={2025},
      eprint={2512.03621},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2512.03621}, 
}