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

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.

Accepted by AAAI 2022

References in corpus (4)

• O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
• MuSCLE: Multi Sweep Compression of LiDAR using Deep Entropy Models
• VoxelContext-Net: An Octree based Framework for Point Cloud Compression
• Attribute Compression of 3D Point Clouds Using Laplacian Sparsity Optimized Graph Transform

Cited by in corpus (8)

• Lossless Point Cloud Geometry and Attribute Compression Using a Learned Conditional Probability Model
• Point Cloud Compression with Sibling Context and Surface Priors
• Enhancing context models for point cloud geometry compression with context feature residuals and multi-loss
• Geometric Prior Based Deep Human Point Cloud Geometry Compression
• Enhancing octree-based context models for point cloud geometry compression with attention-based child node number prediction
• Have We Scene It All? Scene Graph-Aware Deep Point Cloud Compression
• Reflectance Prediction-based Knowledge Distillation for Robust 3D Object Detection in Compressed Point Clouds
• Range Image-Based Implicit Neural Compression for LiDAR Point Clouds