Towards Point Cloud Compression for Machine Perception: A Simple and Strong Baseline by Learning the Octree Depth Level Predictor

TL;DR

This paper introduces a novel octree depth-level predictor for point cloud compression that optimizes bit-rate for machine vision tasks while maintaining quality for human vision, based on adaptive depth level selection.

Contribution

It proposes a scalable point cloud compression framework with an adaptive octree depth predictor, improving machine vision performance without sacrificing human vision quality.

Findings

Enhanced machine vision task performance with adaptive depth levels.

Reduced bit-rate for simpler tasks by using fewer depth levels.

Maintained human vision quality while optimizing for machine tasks.

Abstract

Point cloud compression has garnered significant interest in computer vision. However, existing algorithms primarily cater to human vision, while most point cloud data is utilized for machine vision tasks. To address this, we propose a point cloud compression framework that simultaneously handles both human and machine vision tasks. Our framework learns a scalable bit-stream, using only subsets for different machine vision tasks to save bit-rate, while employing the entire bit-stream for human vision tasks. Building on mainstream octree-based frameworks like VoxelContext-Net, OctAttention, and G-PCC, we introduce a new octree depth-level predictor. This predictor adaptively determines the optimal depth level for each octree constructed from a point cloud, controlling the bit-rate for machine vision tasks. For simpler tasks (\textit{e.g.}, classification) or objects/scenarios, we use fewer depth levels with fewer bits, saving bit-rate. Conversely, for more complex tasks (\textit{e.g}., segmentation) or objects/scenarios, we use deeper depth levels with more bits to enhance performance. Experimental results on various datasets (\textit{e.g}., ModelNet10, ModelNet40, ShapeNet, ScanNet, and KITTI) show that our point cloud compression approach improves performance for machine vision tasks without compromising human vision quality.