Diffusion-Based Generative Models for 3D Occupancy Prediction in Autonomous Driving
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912461538459648 |
|---|---|
| author | Wang, Yunshen Liu, Yicheng Yuan, Tianyuan Liang, Yingshi Yang, Xiuyu Zhang, Honggang Zhao, Hang |
| author_facet | Wang, Yunshen Liu, Yicheng Yuan, Tianyuan Liang, Yingshi Yang, Xiuyu Zhang, Honggang Zhao, Hang |
| contents | Accurately predicting 3D occupancy grids from visual inputs is critical for autonomous driving, but current discriminative methods struggle with noisy data, incomplete observations, and the complex structures inherent in 3D scenes. In this work, we reframe 3D occupancy prediction as a generative modeling task using diffusion models, which learn the underlying data distribution and incorporate 3D scene priors. This approach enhances prediction consistency, noise robustness, and better handles the intricacies of 3D spatial structures. Our extensive experiments show that diffusion-based generative models outperform state-of-the-art discriminative approaches, delivering more realistic and accurate occupancy predictions, especially in occluded or low-visibility regions. Moreover, the improved predictions significantly benefit downstream planning tasks, highlighting the practical advantages of our method for real-world autonomous driving applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23115 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Diffusion-Based Generative Models for 3D Occupancy Prediction in Autonomous Driving Wang, Yunshen Liu, Yicheng Yuan, Tianyuan Liang, Yingshi Yang, Xiuyu Zhang, Honggang Zhao, Hang Computer Vision and Pattern Recognition Accurately predicting 3D occupancy grids from visual inputs is critical for autonomous driving, but current discriminative methods struggle with noisy data, incomplete observations, and the complex structures inherent in 3D scenes. In this work, we reframe 3D occupancy prediction as a generative modeling task using diffusion models, which learn the underlying data distribution and incorporate 3D scene priors. This approach enhances prediction consistency, noise robustness, and better handles the intricacies of 3D spatial structures. Our extensive experiments show that diffusion-based generative models outperform state-of-the-art discriminative approaches, delivering more realistic and accurate occupancy predictions, especially in occluded or low-visibility regions. Moreover, the improved predictions significantly benefit downstream planning tasks, highlighting the practical advantages of our method for real-world autonomous driving applications. |
| title | Diffusion-Based Generative Models for 3D Occupancy Prediction in Autonomous Driving |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.23115 |