LiDARDraft: Generating LiDAR Point Cloud from Versatile Inputs
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911334760710144 |
|---|---|
| author | Wei, Haiyun Lu, Fan Zhu, Yunwei Zheng, Zehan Xue, Weiyi Shao, Lin Zhang, Xudong Wu, Ya Fu, Rong Chen, Guang |
| author_facet | Wei, Haiyun Lu, Fan Zhu, Yunwei Zheng, Zehan Xue, Weiyi Shao, Lin Zhang, Xudong Wu, Ya Fu, Rong Chen, Guang |
| contents | Generating realistic and diverse LiDAR point clouds is crucial for autonomous driving simulation. Although previous methods achieve LiDAR point cloud generation from user inputs, they struggle to attain high-quality results while enabling versatile controllability, due to the imbalance between the complex distribution of LiDAR point clouds and the simple control signals. To address the limitation, we propose LiDARDraft, which utilizes the 3D layout to build a bridge between versatile conditional signals and LiDAR point clouds. The 3D layout can be trivially generated from various user inputs such as textual descriptions and images. Specifically, we represent text, images, and point clouds as unified 3D layouts, which are further transformed into semantic and depth control signals. Then, we employ a rangemap-based ControlNet to guide LiDAR point cloud generation. This pixel-level alignment approach demonstrates excellent performance in controllable LiDAR point clouds generation, enabling "simulation from scratch", allowing self-driving environments to be created from arbitrary textual descriptions, images and sketches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_20105 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LiDARDraft: Generating LiDAR Point Cloud from Versatile Inputs Wei, Haiyun Lu, Fan Zhu, Yunwei Zheng, Zehan Xue, Weiyi Shao, Lin Zhang, Xudong Wu, Ya Fu, Rong Chen, Guang Computer Vision and Pattern Recognition Generating realistic and diverse LiDAR point clouds is crucial for autonomous driving simulation. Although previous methods achieve LiDAR point cloud generation from user inputs, they struggle to attain high-quality results while enabling versatile controllability, due to the imbalance between the complex distribution of LiDAR point clouds and the simple control signals. To address the limitation, we propose LiDARDraft, which utilizes the 3D layout to build a bridge between versatile conditional signals and LiDAR point clouds. The 3D layout can be trivially generated from various user inputs such as textual descriptions and images. Specifically, we represent text, images, and point clouds as unified 3D layouts, which are further transformed into semantic and depth control signals. Then, we employ a rangemap-based ControlNet to guide LiDAR point cloud generation. This pixel-level alignment approach demonstrates excellent performance in controllable LiDAR point clouds generation, enabling "simulation from scratch", allowing self-driving environments to be created from arbitrary textual descriptions, images and sketches. |
| title | LiDARDraft: Generating LiDAR Point Cloud from Versatile Inputs |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.20105 |