SPC-NeRF: Spatial Predictive Compression for Voxel-Based Radiance Field

Representing the Neural Radiance Field (NeRF) with the explicit voxel grid (EVG) is a promising direction for improving NeRFs. However, the EVG representation is not efficient for storage and transmission because of the tremendous memory cost. Existing methods for compressing EVG mainly inherit the methods designed for neural network compression, such as pruning and quantization, which do not take full advantage of the spatial correlation in the voxel grid. Inspired by the prosperous digital image compression techniques, this paper proposes SPC-NeRF, a novel framework applying spatial predictive coding in EVG NeRF compression. The proposed framework can remove spatial redundancy efficiently for better compression performance. Our framework contains a progressive coding procedure to realize adaptive quantization precision according to the different importance of the voxels. Moreover, we model the coding bitrate of our framework and design a novel form of the loss function. With the loss function, we can jointly optimize the compression ratio and the rendering distortion to achieve higher coding efficiency. Extensive experiments demonstrate that our method can achieve 32% bit saving compared to the benchmark method VQRF on multiple representative test datasets, with comparable training time.