OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries
This work addresses computational demands and detail loss in 3D scene understanding for applications like autonomous driving or robotics, representing an incremental improvement over dense-grid methods.
The paper tackles the problem of computational inefficiency and loss of spatial details in 3D occupancy prediction by introducing OctreeOcc, a framework that uses octree representations and iterative refinement, achieving a 15%-24% reduction in computational overhead while surpassing state-of-the-art methods.
Occupancy prediction has increasingly garnered attention in recent years for its fine-grained understanding of 3D scenes. Traditional approaches typically rely on dense, regular grid representations, which often leads to excessive computational demands and a loss of spatial details for small objects. This paper introduces OctreeOcc, an innovative 3D occupancy prediction framework that leverages the octree representation to adaptively capture valuable information in 3D, offering variable granularity to accommodate object shapes and semantic regions of varying sizes and complexities. In particular, we incorporate image semantic information to improve the accuracy of initial octree structures and design an effective rectification mechanism to refine the octree structure iteratively. Our extensive evaluations show that OctreeOcc not only surpasses state-of-the-art methods in occupancy prediction, but also achieves a 15%-24% reduction in computational overhead compared to dense-grid-based methods.