LowRankOcc: Tensor Decomposition and Low-Rank Recovery for Vision-Based 3D Semantic Occupancy Prediction
Lists
Only you see this
Abstract
In this paper, we present a tensor decomposition and low-rank recovery approach (LowRankOcc) for vision-based 3D semantic occupancy prediction. Conventional methods model outdoor scenes with fine-grained 3D grids, but the sparsity of non-empty voxels introduces consider-able spatial redundancy, leading to potential overfitting risks. In contrast, our approach leverages the intrinsic low-rank property of 3D occupancy data, factorizing voxel representations into low-rank components to efficiently mitigate spatial redundancy without sacrificing performance. Specifically, we present the Vertical-Horizontal (VH) de-composition block factorizes 3D tensors into vertical vectors and horizontal matrices. With our “decomposition-encoding-recovery” framework, we encode 3D contexts with only 1/2D convolutions and poolings, and subsequently recover the encoded compact yet informative context features back to voxel representations. Experimental results demonstrate that LowRankOcc achieves state-of-the-art performances in semantic scene completion on the Se-manticKITTI dataset and 3D occupancy prediction on the nuScenes dataset.
BibTeX
@inproceedings{zhao2024lowrankocc,
author = {Linqing Zhao and Xiuwei Xu and Ziwei Wang and Yunpeng Zhang and Borui Zhang and Wenzhao Zheng and Dalong Du and Jie Zhou and Jiwen Lu},
title = {{LowRankOcc: Tensor Decomposition and Low-Rank Recovery for Vision-Based 3D Semantic Occupancy Prediction}},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2024},
doi = {10.1109/cvpr52733.2024.00936},
}Loading related content...