- [2026/01/27] We release the code and pretrained weights.
- [2026/01/21] SuperOcc is on Arxiv.
3D occupancy prediction plays a pivotal role in the realm of autonomous driving, as it provides a comprehensive understanding of the driving environment. Most existing methods construct dense scene representations for occupancy prediction, overlooking the inherent sparsity of real-world driving scenes. Recently, 3D superquadric representation has emerged as a promising sparse alternative to dense scene representations due to the strong geometric expressiveness of superquadrics. However, existing superquadric frameworks still suffer from insufficient temporal modeling, a challenging trade-off between query sparsity and geometric expressiveness, and inefficient superquadric-to-voxel splatting. To address these issues, we propose SuperOcc, a novel framework for superquadric-based 3D occupancy prediction. SuperOcc incorporates three key designs: (1) a cohesive temporal modeling mechanism to simultaneously exploit view-centric and object-centric temporal cues; (2) a multi-superquadric decoding strategy to enhance geometric expressiveness without sacrificing query sparsity; and (3) an efficient superquadric-to-voxel splatting scheme to improve computational efficiency. Extensive experiments on the SurroundOcc and Occ3D benchmarks demonstrate that SuperOcc achieves state-of-the-art performance while maintaining superior efficiency.
| Models | Epochs | Q | mIoU | RayIoU | FPS | Link |
|---|---|---|---|---|---|---|
| SuperOcc-T | 48 | 600 | 36.1 | 42.5 | 30.3 | Model |
| SuperOcc-S | 48 | 1200 | 36.9 | 43.0 | 28.2 | Model |
| SuperOcc-M | 48 | 2400 | 37.4 | 43.6 | 18.8 | Model |
| SuperOcc-L | 48 | 3600 | 38.1 | 44.0 | 12.7 | Model |
| Models | Epochs | Q | IoU | mIoU | FPS | Link |
|---|---|---|---|---|---|---|
| SuperOcc-T | 24 | 600 | 34.91 | 22.48 | 30.3 | Model |
| SuperOcc-S | 24 | 1200 | 35.63 | 23.12 | 28.2 | Model |
| SuperOcc-M | 24 | 2400 | 36.99 | 23.95 | 18.8 | Model |
| SuperOcc-L | 24 | 3600 | 38.13 | 24.55 | 12.7 | Model |
Many thanks to these excellent open-source projects:
- 3D Occupancy: QuadricFormer OPUS SparseOcc
- 3D Detection: StreamPETR
- Codebase: MMDetection3D
If this work is helpful for your research, please consider citing the following BibTeX entry.
@article{yu2026superocc,
title={SuperOcc: Toward Cohesive Temporal Modeling for Superquadric-based Occupancy Prediction},
author={Yu, Zichen and Liu, Quanli and Wang, Wei and Zhang, Liyong and Zhao, Xiaoguang},
journal={arXiv preprint arXiv:2601.15644},
year={2026}
}