LiDAR-EDIT: LiDAR Data Generation by Editing the Object Layouts in Real-World Scenes
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915302603751424 |
|---|---|
| author | Ho, Shing-Hei Thach, Bao Zhu, Minghan |
| author_facet | Ho, Shing-Hei Thach, Bao Zhu, Minghan |
| contents | We present LiDAR-EDIT, a novel paradigm for generating synthetic LiDAR data for autonomous driving. Our framework edits real-world LiDAR scans by introducing new object layouts while preserving the realism of the background environment. Compared to end-to-end frameworks that generate LiDAR point clouds from scratch, LiDAR-EDIT offers users full control over the object layout, including the number, type, and pose of objects, while keeping most of the original real-world background. Our method also provides object labels for the generated data. Compared to novel view synthesis techniques, our framework allows for the creation of counterfactual scenarios with object layouts significantly different from the original real-world scene. LiDAR-EDIT uses spherical voxelization to enforce correct LiDAR projective geometry in the generated point clouds by construction. During object removal and insertion, generative models are employed to fill the unseen background and object parts that were occluded in the original real LiDAR scans. Experimental results demonstrate that our framework produces realistic LiDAR scans with practical value for downstream tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_00592 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LiDAR-EDIT: LiDAR Data Generation by Editing the Object Layouts in Real-World Scenes Ho, Shing-Hei Thach, Bao Zhu, Minghan Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics We present LiDAR-EDIT, a novel paradigm for generating synthetic LiDAR data for autonomous driving. Our framework edits real-world LiDAR scans by introducing new object layouts while preserving the realism of the background environment. Compared to end-to-end frameworks that generate LiDAR point clouds from scratch, LiDAR-EDIT offers users full control over the object layout, including the number, type, and pose of objects, while keeping most of the original real-world background. Our method also provides object labels for the generated data. Compared to novel view synthesis techniques, our framework allows for the creation of counterfactual scenarios with object layouts significantly different from the original real-world scene. LiDAR-EDIT uses spherical voxelization to enforce correct LiDAR projective geometry in the generated point clouds by construction. During object removal and insertion, generative models are employed to fill the unseen background and object parts that were occluded in the original real LiDAR scans. Experimental results demonstrate that our framework produces realistic LiDAR scans with practical value for downstream tasks. |
| title | LiDAR-EDIT: LiDAR Data Generation by Editing the Object Layouts in Real-World Scenes |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics |
| url | https://arxiv.org/abs/2412.00592 |