GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913600023560192 |
|---|---|
| author | Huang, Yuanhui Thammatadatrakoon, Amonnut Zheng, Wenzhao Zhang, Yunpeng Du, Dalong Lu, Jiwen |
| author_facet | Huang, Yuanhui Thammatadatrakoon, Amonnut Zheng, Wenzhao Zhang, Yunpeng Du, Dalong Lu, Jiwen |
| contents | 3D semantic occupancy prediction is an important task for robust vision-centric autonomous driving, which predicts fine-grained geometry and semantics of the surrounding scene. Most existing methods leverage dense grid-based scene representations, overlooking the spatial sparsity of the driving scenes. Although 3D semantic Gaussian serves as an object-centric sparse alternative, most of the Gaussians still describe the empty region with low efficiency. To address this, we propose a probabilistic Gaussian superposition model which interprets each Gaussian as a probability distribution of its neighborhood being occupied and conforms to probabilistic multiplication to derive the overall geometry. Furthermore, we adopt the exact Gaussian mixture model for semantics calculation to avoid unnecessary overlapping of Gaussians. To effectively initialize Gaussians in non-empty region, we design a distribution-based initialization module which learns the pixel-aligned occupancy distribution instead of the depth of surfaces. We conduct extensive experiments on nuScenes and KITTI-360 datasets and our GaussianFormer-2 achieves state-of-the-art performance with high efficiency. Code: https://github.com/huang-yh/GaussianFormer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_04384 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction Huang, Yuanhui Thammatadatrakoon, Amonnut Zheng, Wenzhao Zhang, Yunpeng Du, Dalong Lu, Jiwen Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning 3D semantic occupancy prediction is an important task for robust vision-centric autonomous driving, which predicts fine-grained geometry and semantics of the surrounding scene. Most existing methods leverage dense grid-based scene representations, overlooking the spatial sparsity of the driving scenes. Although 3D semantic Gaussian serves as an object-centric sparse alternative, most of the Gaussians still describe the empty region with low efficiency. To address this, we propose a probabilistic Gaussian superposition model which interprets each Gaussian as a probability distribution of its neighborhood being occupied and conforms to probabilistic multiplication to derive the overall geometry. Furthermore, we adopt the exact Gaussian mixture model for semantics calculation to avoid unnecessary overlapping of Gaussians. To effectively initialize Gaussians in non-empty region, we design a distribution-based initialization module which learns the pixel-aligned occupancy distribution instead of the depth of surfaces. We conduct extensive experiments on nuScenes and KITTI-360 datasets and our GaussianFormer-2 achieves state-of-the-art performance with high efficiency. Code: https://github.com/huang-yh/GaussianFormer. |
| title | GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2412.04384 |