EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909553754374144 |
|---|---|
| author | Miao, Sheng Huang, Jiaxin Bai, Dongfeng Yan, Xu Zhou, Hongyu Wang, Yue Liu, Bingbing Geiger, Andreas Liao, Yiyi |
| author_facet | Miao, Sheng Huang, Jiaxin Bai, Dongfeng Yan, Xu Zhou, Hongyu Wang, Yue Liu, Bingbing Geiger, Andreas Liao, Yiyi |
| contents | Novel view synthesis of urban scenes is essential for autonomous driving-related applications.Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization. We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner. Unlike existing feed-forward, pixel-aligned 3DGS methods, which often suffer from issues like multi-view inconsistencies and duplicated content, our approach predicts 3D Gaussians across multiple frames within a unified volume using a 3D convolutional network. This is achieved by initializing 3D Gaussians with noisy depth predictions, and then refining their geometric properties in 3D space and predicting color based on 2D textures. Our model also handles distant views and the sky with a flexible hemisphere background model. This enables us to perform fast, feed-forward reconstruction while achieving real-time rendering. Experimental evaluations on the KITTI-360 and Waymo datasets show that our method achieves state-of-the-art quality compared to existing feed-forward 3DGS- and NeRF-based methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_20168 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis Miao, Sheng Huang, Jiaxin Bai, Dongfeng Yan, Xu Zhou, Hongyu Wang, Yue Liu, Bingbing Geiger, Andreas Liao, Yiyi Computer Vision and Pattern Recognition Novel view synthesis of urban scenes is essential for autonomous driving-related applications.Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization. We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner. Unlike existing feed-forward, pixel-aligned 3DGS methods, which often suffer from issues like multi-view inconsistencies and duplicated content, our approach predicts 3D Gaussians across multiple frames within a unified volume using a 3D convolutional network. This is achieved by initializing 3D Gaussians with noisy depth predictions, and then refining their geometric properties in 3D space and predicting color based on 2D textures. Our model also handles distant views and the sky with a flexible hemisphere background model. This enables us to perform fast, feed-forward reconstruction while achieving real-time rendering. Experimental evaluations on the KITTI-360 and Waymo datasets show that our method achieves state-of-the-art quality compared to existing feed-forward 3DGS- and NeRF-based methods. |
| title | EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.20168 |