FlexDrive: Toward Trajectory Flexibility in Driving Scene Reconstruction and Rendering
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929737872441344 |
|---|---|
| author | Zhou, Jingqiu Fan, Lue Huang, Linjiang Shi, Xiaoyu Liu, Si Zhang, Zhaoxiang Li, Hongsheng |
| author_facet | Zhou, Jingqiu Fan, Lue Huang, Linjiang Shi, Xiaoyu Liu, Si Zhang, Zhaoxiang Li, Hongsheng |
| contents | Driving scene reconstruction and rendering have advanced significantly using the 3D Gaussian Splatting. However, most prior research has focused on the rendering quality along a pre-recorded vehicle path and struggles to generalize to out-of-path viewpoints, which is caused by the lack of high-quality supervision in those out-of-path views. To address this issue, we introduce an Inverse View Warping technique to create compact and high-quality images as supervision for the reconstruction of the out-of-path views, enabling high-quality rendering results for those views. For accurate and robust inverse view warping, a depth bootstrap strategy is proposed to obtain on-the-fly dense depth maps during the optimization process, overcoming the sparsity and incompleteness of LiDAR depth data. Our method achieves superior in-path and out-of-path reconstruction and rendering performance on the widely used Waymo Open dataset. In addition, a simulator-based benchmark is proposed to obtain the out-of-path ground truth and quantitatively evaluate the performance of out-of-path rendering, where our method outperforms previous methods by a significant margin. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_21093 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FlexDrive: Toward Trajectory Flexibility in Driving Scene Reconstruction and Rendering Zhou, Jingqiu Fan, Lue Huang, Linjiang Shi, Xiaoyu Liu, Si Zhang, Zhaoxiang Li, Hongsheng Computer Vision and Pattern Recognition Driving scene reconstruction and rendering have advanced significantly using the 3D Gaussian Splatting. However, most prior research has focused on the rendering quality along a pre-recorded vehicle path and struggles to generalize to out-of-path viewpoints, which is caused by the lack of high-quality supervision in those out-of-path views. To address this issue, we introduce an Inverse View Warping technique to create compact and high-quality images as supervision for the reconstruction of the out-of-path views, enabling high-quality rendering results for those views. For accurate and robust inverse view warping, a depth bootstrap strategy is proposed to obtain on-the-fly dense depth maps during the optimization process, overcoming the sparsity and incompleteness of LiDAR depth data. Our method achieves superior in-path and out-of-path reconstruction and rendering performance on the widely used Waymo Open dataset. In addition, a simulator-based benchmark is proposed to obtain the out-of-path ground truth and quantitatively evaluate the performance of out-of-path rendering, where our method outperforms previous methods by a significant margin. |
| title | FlexDrive: Toward Trajectory Flexibility in Driving Scene Reconstruction and Rendering |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.21093 |