RENO: Real-Time Neural Compression for 3D LiDAR Point Clouds
This addresses the need for efficient compression in industrial applications like autonomous vehicles, though it is incremental as it builds on existing neural methods.
The paper tackles the challenge of real-time neural compression for 3D LiDAR point clouds by proposing RENO, which achieves real-time coding at 10 fps with 12.25% and 48.34% bit-rate savings compared to G-PCCv23 and Draco, respectively, while using a 1MB model.
Despite the substantial advancements demonstrated by learning-based neural models in the LiDAR Point Cloud Compression (LPCC) task, realizing real-time compression - an indispensable criterion for numerous industrial applications - remains a formidable challenge. This paper proposes RENO, the first real-time neural codec for 3D LiDAR point clouds, achieving superior performance with a lightweight model. RENO skips the octree construction and directly builds upon the multiscale sparse tensor representation. Instead of the multi-stage inferring, RENO devises sparse occupancy codes, which exploit cross-scale correlation and derive voxels' occupancy in a one-shot manner, greatly saving processing time. Experimental results demonstrate that the proposed RENO achieves real-time coding speed, 10 fps at 14-bit depth on a desktop platform (e.g., one RTX 3090 GPU) for both encoding and decoding processes, while providing 12.25% and 48.34% bit-rate savings compared to G-PCCv23 and Draco, respectively, at a similar quality. RENO model size is merely 1MB, making it attractive for practical applications. The source code is available at https://github.com/NJUVISION/RENO.