OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression

TL;DR

OctAttention introduces an octree-based deep learning framework for point cloud compression, leveraging sibling and ancestor contexts with attention mechanisms to improve efficiency and compression performance significantly.

Contribution

The paper proposes a novel octree-based deep learning model with a large receptive field and attention mechanism for improved point cloud compression.

Findings

Achieves 10%-35% BD-Rate gain on benchmarks

Reduces coding time by 95% compared to voxel-based methods

Robustly handles sparse point clouds with different resolutions

Abstract

In point cloud compression, sufficient contexts are significant for modeling the point cloud distribution. However, the contexts gathered by the previous voxel-based methods decrease when handling sparse point clouds. To address this problem, we propose a multiple-contexts deep learning framework called OctAttention employing the octree structure, a memory-efficient representation for point clouds. Our approach encodes octree symbol sequences in a lossless way by gathering the information of sibling and ancestor nodes. Expressly, we first represent point clouds with octree to reduce spatial redundancy, which is robust for point clouds with different resolutions. We then design a conditional entropy model with a large receptive field that models the sibling and ancestor contexts to exploit the strong dependency among the neighboring nodes and employ an attention mechanism to emphasize the correlated nodes in the context. Furthermore, we introduce a mask operation during training and testing to make a trade-off between encoding time and performance. Compared to the previous state-of-the-art works, our approach obtains a 10%-35% BD-Rate gain on the LiDAR benchmark (e.g. SemanticKITTI) and object point cloud dataset (e.g. MPEG 8i, MVUB), and saves 95% coding time compared to the voxel-based baseline. The code is available at https://github.com/zb12138/OctAttention.