Patch-Based Deep Autoencoder for Point Cloud Geometry Compression
This addresses compression needs for 3D applications like virtual reality, but it is incremental as it builds on existing deep learning methods by introducing a patch-based approach.
The paper tackles point cloud geometry compression by proposing a patch-based deep autoencoder that processes patches independently and assembles them after decompression, achieving state-of-the-art rate-distortion performance, particularly at low bitrates, and ensuring the output has the same number of points as the input.
The ever-increasing 3D application makes the point cloud compression unprecedentedly important and needed. In this paper, we propose a patch-based compression process using deep learning, focusing on the lossy point cloud geometry compression. Unlike existing point cloud compression networks, which apply feature extraction and reconstruction on the entire point cloud, we divide the point cloud into patches and compress each patch independently. In the decoding process, we finally assemble the decompressed patches into a complete point cloud. In addition, we train our network by a patch-to-patch criterion, i.e., use the local reconstruction loss for optimization, to approximate the global reconstruction optimality. Our method outperforms the state-of-the-art in terms of rate-distortion performance, especially at low bitrates. Moreover, the compression process we proposed can guarantee to generate the same number of points as the input. The network model of this method can be easily applied to other point cloud reconstruction problems, such as upsampling.