QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916792194039808 |
|---|---|
| author | Zuo, Sicheng Zheng, Wenzhao Han, Xiaoyong Yang, Longchao Pan, Yong Lu, Jiwen |
| author_facet | Zuo, Sicheng Zheng, Wenzhao Han, Xiaoyong Yang, Longchao Pan, Yong Lu, Jiwen |
| contents | 3D occupancy prediction is crucial for robust autonomous driving systems as it enables comprehensive perception of environmental structures and semantics. Most existing methods employ dense voxel-based scene representations, ignoring the sparsity of driving scenes and resulting in inefficiency. Recent works explore object-centric representations based on sparse Gaussians, but their ellipsoidal shape prior limits the modeling of diverse structures. In real-world driving scenes, objects exhibit rich geometries (e.g., cuboids, cylinders, and irregular shapes), necessitating excessive ellipsoidal Gaussians densely packed for accurate modeling, which leads to inefficient representations. To address this, we propose to use geometrically expressive superquadrics as scene primitives, enabling efficient representation of complex structures with fewer primitives through their inherent shape diversity. We develop a probabilistic superquadric mixture model, which interprets each superquadric as an occupancy probability distribution with a corresponding geometry prior, and calculates semantics through probabilistic mixture. Building on this, we present QuadricFormer, a superquadric-based model for efficient 3D occupancy prediction, and introduce a pruning-and-splitting module to further enhance modeling efficiency by concentrating superquadrics in occupied regions. Extensive experiments on the nuScenes dataset demonstrate that QuadricFormer achieves state-of-the-art performance while maintaining superior efficiency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_10977 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction Zuo, Sicheng Zheng, Wenzhao Han, Xiaoyong Yang, Longchao Pan, Yong Lu, Jiwen Computer Vision and Pattern Recognition 3D occupancy prediction is crucial for robust autonomous driving systems as it enables comprehensive perception of environmental structures and semantics. Most existing methods employ dense voxel-based scene representations, ignoring the sparsity of driving scenes and resulting in inefficiency. Recent works explore object-centric representations based on sparse Gaussians, but their ellipsoidal shape prior limits the modeling of diverse structures. In real-world driving scenes, objects exhibit rich geometries (e.g., cuboids, cylinders, and irregular shapes), necessitating excessive ellipsoidal Gaussians densely packed for accurate modeling, which leads to inefficient representations. To address this, we propose to use geometrically expressive superquadrics as scene primitives, enabling efficient representation of complex structures with fewer primitives through their inherent shape diversity. We develop a probabilistic superquadric mixture model, which interprets each superquadric as an occupancy probability distribution with a corresponding geometry prior, and calculates semantics through probabilistic mixture. Building on this, we present QuadricFormer, a superquadric-based model for efficient 3D occupancy prediction, and introduce a pruning-and-splitting module to further enhance modeling efficiency by concentrating superquadrics in occupied regions. Extensive experiments on the nuScenes dataset demonstrate that QuadricFormer achieves state-of-the-art performance while maintaining superior efficiency. |
| title | QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.10977 |