Density-preserving Deep Point Cloud Compression
This work addresses the need for efficient point cloud compression in applications like autonomous driving and 3D modeling, though it is incremental as it builds on existing auto-encoder methods.
The paper tackles the problem of point cloud compression by preserving local density information, which is often overlooked, and achieves state-of-the-art rate-distortion trade-off on datasets like SemanticKITTI and ShapeNet.
Local density of point clouds is crucial for representing local details, but has been overlooked by existing point cloud compression methods. To address this, we propose a novel deep point cloud compression method that preserves local density information. Our method works in an auto-encoder fashion: the encoder downsamples the points and learns point-wise features, while the decoder upsamples the points using these features. Specifically, we propose to encode local geometry and density with three embeddings: density embedding, local position embedding and ancestor embedding. During the decoding, we explicitly predict the upsampling factor for each point, and the directions and scales of the upsampled points. To mitigate the clustered points issue in existing methods, we design a novel sub-point convolution layer, and an upsampling block with adaptive scale. Furthermore, our method can also compress point-wise attributes, such as normal. Extensive qualitative and quantitative results on SemanticKITTI and ShapeNet demonstrate that our method achieves the state-of-the-art rate-distortion trade-off.