English

CodedVTR: Codebook-based Sparse Voxel Transformer with Geometric Guidance

Computer Vision and Pattern Recognition 2022-03-29 v2

Abstract

Transformers have gained much attention by outperforming convolutional neural networks in many 2D vision tasks. However, they are known to have generalization problems and rely on massive-scale pre-training and sophisticated training techniques. When applying to 3D tasks, the irregular data structure and limited data scale add to the difficulty of transformer's application. We propose CodedVTR (Codebook-based Voxel TRansformer), which improves data efficiency and generalization ability for 3D sparse voxel transformers. On the one hand, we propose the codebook-based attention that projects an attention space into its subspace represented by the combination of "prototypes" in a learnable codebook. It regularizes attention learning and improves generalization. On the other hand, we propose geometry-aware self-attention that utilizes geometric information (geometric pattern, density) to guide attention learning. CodedVTR could be embedded into existing sparse convolution-based methods, and bring consistent performance improvements for indoor and outdoor 3D semantic segmentation tasks

Keywords

Cite

@article{arxiv.2203.09887,
  title  = {CodedVTR: Codebook-based Sparse Voxel Transformer with Geometric Guidance},
  author = {Tianchen Zhao and Niansong Zhang and Xuefei Ning and He Wang and Li Yi and Yu Wang},
  journal= {arXiv preprint arXiv:2203.09887},
  year   = {2022}
}

Comments

Published at CVPR2022

R2 v1 2026-06-24T10:18:15.791Z