OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression
This addresses the storage challenge for LiDAR data in applications like self-driving cars, where vehicles capture billions of points daily, representing an incremental improvement over existing compression techniques.
The paper tackles the problem of compressing LiDAR point clouds to reduce memory footprint, achieving a 10-20% bitrate reduction at the same reconstruction quality compared to previous state-of-the-art methods and improving performance in downstream 3D segmentation and detection tasks at the same bitrate.
We present a novel deep compression algorithm to reduce the memory footprint of LiDAR point clouds. Our method exploits the sparsity and structural redundancy between points to reduce the bitrate. Towards this goal, we first encode the LiDAR points into an octree, a data-efficient structure suitable for sparse point clouds. We then design a tree-structured conditional entropy model that models the probabilities of the octree symbols to encode the octree into a compact bitstream. We validate the effectiveness of our method over two large-scale datasets. The results demonstrate that our approach reduces the bitrate by 10-20% at the same reconstruction quality, compared to the previous state-of-the-art. Importantly, we also show that for the same bitrate, our approach outperforms other compression algorithms when performing downstream 3D segmentation and detection tasks using compressed representations. Our algorithm can be used to reduce the onboard and offboard storage of LiDAR points for applications such as self-driving cars, where a single vehicle captures 84 billion points per day