D-Compress: Detail-Preserving LiDAR Range Image Compression for Real-Time Streaming on Resource-Constrained Robots

2026-03-13

AI Summary

This work addresses the limitations of existing image codec-based LiDAR point cloud compression methods, which often sacrifice geometric fidelity due to human visual system-oriented optimization and lack effective rate control under dynamic bandwidth conditions, thereby degrading downstream task performance. To overcome these issues, we propose D-Compress, a novel framework that integrates a detail-preserving mechanism with rate-distortion optimized (RDO) bitrate control tailored for LiDAR range images. By leveraging intra- and inter-frame prediction alongside adaptive discrete wavelet transform for efficient residual compression, D-Compress achieves superior performance even at compression ratios exceeding 100×. It consistently maintains high geometric accuracy and task performance across multiple datasets, while enabling real-time streaming on resource-constrained devices with robust and efficient bitrate adaptation under varying bandwidth conditions.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Data Mining & Knowledge Management: Data Compression
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Efficient 3D LiDAR point cloud compression (LPCC) and streaming are critical for edge server-assisted robotic systems, enabling real-time communication with compact data representations. A widely adopted approach represents LiDAR point clouds as range images, enabling the direct use of mature image and video compression codecs. However, because these codecs are designed with human visual perception in mind, they often compromise geometric details, which downgrades the performance of downstream robotic tasks such as mapping and object detection. Furthermore, rate-distortion optimization (RDO)-based rate control remains largely underexplored for range image compression (RIC) under dynamic bandwidth conditions. To address these limitations, we propose D-Compress, a new detail-preserving and fast RIC framework tailored for real-time streaming. D-Compress integrates both intra- and inter-frame prediction with an adaptive discrete wavelet transform approach for precise residual compression. Additionally, we introduce a new RDO-based rate control algorithm for RIC through new rate-distortion modeling. Extensive evaluations on various datasets demonstrate the superiority of D-Compress, which outperforms state-of-the-art (SOTA) compression methods in both geometric accuracy and downstream task performance, particularly at compression ratios exceeding 100x, while maintaining real-time execution on resource-constrained hardware. Moreover, evaluations under dynamic bandwidth conditions validate the robustness of its rate control mechanism.

Problem

• LiDAR range image compression
• detail preservation
• rate-distortion optimization
• real-time streaming
• resource-constrained robots

Innovation

• LiDAR range image compression
• detail-preserving compression
• rate-distortion optimization
• adaptive discrete wavelet transform
• real-time streaming