Real-time Neural Rendering of LiDAR Point Clouds
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918127655190528 |
|---|---|
| author | Vanherck, Joni Zoomers, Brent Mertens, Tom Jorissen, Lode Michiels, Nick |
| author_facet | Vanherck, Joni Zoomers, Brent Mertens, Tom Jorissen, Lode Michiels, Nick |
| contents | Static LiDAR scanners produce accurate, dense, colored point clouds, but often contain obtrusive artifacts which makes them ill-suited for direct display. We propose an efficient method to render photorealistic images of such scans without any expensive preprocessing or training of a scene-specific model. A naive projection of the point cloud to the output view using 1x1 pixels is fast and retains the available detail, but also results in unintelligible renderings as background points leak in between the foreground pixels. The key insight is that these projections can be transformed into a realistic result using a deep convolutional model in the form of a U-Net, and a depth-based heuristic that prefilters the data. The U-Net also handles LiDAR-specific problems such as missing parts due to occlusion, color inconsistencies and varying point densities. We also describe a method to generate synthetic training data to deal with imperfectly-aligned ground truth images. Our method achieves real-time rendering rates using an off-the-shelf GPU and outperforms the state-of-the-art in both speed and quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_11618 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Real-time Neural Rendering of LiDAR Point Clouds Vanherck, Joni Zoomers, Brent Mertens, Tom Jorissen, Lode Michiels, Nick Computer Vision and Pattern Recognition Graphics Static LiDAR scanners produce accurate, dense, colored point clouds, but often contain obtrusive artifacts which makes them ill-suited for direct display. We propose an efficient method to render photorealistic images of such scans without any expensive preprocessing or training of a scene-specific model. A naive projection of the point cloud to the output view using 1x1 pixels is fast and retains the available detail, but also results in unintelligible renderings as background points leak in between the foreground pixels. The key insight is that these projections can be transformed into a realistic result using a deep convolutional model in the form of a U-Net, and a depth-based heuristic that prefilters the data. The U-Net also handles LiDAR-specific problems such as missing parts due to occlusion, color inconsistencies and varying point densities. We also describe a method to generate synthetic training data to deal with imperfectly-aligned ground truth images. Our method achieves real-time rendering rates using an off-the-shelf GPU and outperforms the state-of-the-art in both speed and quality. |
| title | Real-time Neural Rendering of LiDAR Point Clouds |
| topic | Computer Vision and Pattern Recognition Graphics |
| url | https://arxiv.org/abs/2502.11618 |