LVAC: Learned Volumetric Attribute Compression for Point Clouds using Coordinate Based Networks
This work addresses attribute compression for point clouds, with potential applications in fields like 3D graphics and neural radiance fields, though it is incremental as it builds on existing methods like G-PCC.
The paper tackles the problem of compressing point cloud attributes by modeling them as a volumetric function and compressing its parameters using coordinate-based neural networks, achieving a 2-4 dB improvement over the existing RAHT method.
We consider the attributes of a point cloud as samples of a vector-valued volumetric function at discrete positions. To compress the attributes given the positions, we compress the parameters of the volumetric function. We model the volumetric function by tiling space into blocks, and representing the function over each block by shifts of a coordinate-based, or implicit, neural network. Inputs to the network include both spatial coordinates and a latent vector per block. We represent the latent vectors using coefficients of the region-adaptive hierarchical transform (RAHT) used in the MPEG geometry-based point cloud codec G-PCC. The coefficients, which are highly compressible, are rate-distortion optimized by back-propagation through a rate-distortion Lagrangian loss in an auto-decoder configuration. The result outperforms RAHT by 2--4 dB. This is the first work to compress volumetric functions represented by local coordinate-based neural networks. As such, we expect it to be applicable beyond point clouds, for example to compression of high-resolution neural radiance fields.