UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911465141698560 |
|---|---|
| author | Tan, Kaiyuan Shen, Yingying Tu, Mingfei Zhu, Haohui Wang, Bing Chen, Guang Ye, Hangjun Sun, Haiyang |
| author_facet | Tan, Kaiyuan Shen, Yingying Tu, Mingfei Zhu, Haohui Wang, Bing Chen, Guang Ye, Hangjun Sun, Haiyang |
| contents | Dynamic driving scene reconstruction is critical for autonomous driving simulation and closed-loop learning. While recent feed-forward methods have shown promise for 3D reconstruction, they struggle with long-range driving sequences due to quadratic complexity in sequence length and challenges in modeling dynamic objects over extended durations. We propose UFO, a novel recurrent paradigm that combines the benefits of optimization-based and feed-forward methods for efficient long-range 4D reconstruction. Our approach maintains a 4D scene representation that is iteratively refined as new observations arrive, using a visibility-based filtering mechanism to select informative scene tokens and enable efficient processing of long sequences. For dynamic objects, we introduce an object pose-guided modeling approach that supports accurate long-range motion capture. Experiments on the Waymo Open Dataset demonstrate that our method significantly outperforms both per-scene optimization and existing feed-forward methods across various sequence lengths. Notably, our approach can reconstruct 16-second driving logs within 0.5 second while maintaining superior visual quality and geometric accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_20943 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling Tan, Kaiyuan Shen, Yingying Tu, Mingfei Zhu, Haohui Wang, Bing Chen, Guang Ye, Hangjun Sun, Haiyang Computer Vision and Pattern Recognition Dynamic driving scene reconstruction is critical for autonomous driving simulation and closed-loop learning. While recent feed-forward methods have shown promise for 3D reconstruction, they struggle with long-range driving sequences due to quadratic complexity in sequence length and challenges in modeling dynamic objects over extended durations. We propose UFO, a novel recurrent paradigm that combines the benefits of optimization-based and feed-forward methods for efficient long-range 4D reconstruction. Our approach maintains a 4D scene representation that is iteratively refined as new observations arrive, using a visibility-based filtering mechanism to select informative scene tokens and enable efficient processing of long sequences. For dynamic objects, we introduce an object pose-guided modeling approach that supports accurate long-range motion capture. Experiments on the Waymo Open Dataset demonstrate that our method significantly outperforms both per-scene optimization and existing feed-forward methods across various sequence lengths. Notably, our approach can reconstruct 16-second driving logs within 0.5 second while maintaining superior visual quality and geometric accuracy. |
| title | UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.20943 |