SuperOcc: Toward Cohesive Temporal Modeling for Superquadric-based 3D Occupancy Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yu, Zichen, Liu, Quanli, Wang, Wei, Zhang, Liyong, Zhao, Xiaoguang
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908899105308672
author Yu, Zichen
Liu, Quanli
Wang, Wei
Zhang, Liyong
Zhao, Xiaoguang
author_facet Yu, Zichen
Liu, Quanli
Wang, Wei
Zhang, Liyong
Zhao, Xiaoguang
contents 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. The code is available at https://github.com/Yzichen/SuperOcc.
format Preprint
id arxiv_https___arxiv_org_abs_2601_15644
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SuperOcc: Toward Cohesive Temporal Modeling for Superquadric-based 3D Occupancy Prediction
Yu, Zichen
Liu, Quanli
Wang, Wei
Zhang, Liyong
Zhao, Xiaoguang
Computer Vision and Pattern Recognition
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. The code is available at https://github.com/Yzichen/SuperOcc.
title SuperOcc: Toward Cohesive Temporal Modeling for Superquadric-based 3D Occupancy Prediction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.15644