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

2026-01-22

AI Summary

Existing superquadric-based 3D occupancy prediction methods struggle to balance temporal modeling, geometric expressiveness, and query sparsity, while also suffering from inefficient voxel splatting. To address these limitations, this work proposes SuperOcc, a novel framework that unifies view-centric and object-centric temporal cues, introduces a multi-superquadric decoding strategy to effectively trade off sparsity against geometric fidelity, and designs an efficient superquadric-to-voxel splatting mechanism. Evaluated on the SurroundOcc and Occ3D benchmarks, SuperOcc achieves state-of-the-art performance while maintaining high computational efficiency.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Computer Vision: 3D Computer Vision
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

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.

Problem

• temporal modeling
• superquadric
• occupancy prediction
• geometric expressiveness
• query sparsity

Innovation

• superquadric
• temporal modeling
• occupancy prediction
• sparse representation
• efficient splatting