SPC-NeRF: Spatial Predictive Compression for Voxel Based Radiance Field
This addresses storage and transmission inefficiencies for 3D scene representations in computer vision, though it is incremental as it builds on existing voxel-based NeRF methods.
The paper tackles the high memory cost of explicit voxel grid representations in Neural Radiance Fields (NeRF) by proposing SPC-NeRF, a compression framework that uses spatial predictive coding to remove redundancy, achieving a 32% bit saving compared to the state-of-the-art method VQRF on multiple datasets.
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 terrific memory cost. Current 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 of voxels. Inspired by prosperous digital image compression techniques, this paper proposes SPC-NeRF, a novel framework applying spatial predictive coding in EVG compression. The proposed framework can remove spatial redundancy efficiently for better compression performance.Moreover, we model the bitrate and design a novel form of the loss function, where we can jointly optimize compression ratio and distortion to achieve higher coding efficiency. Extensive experiments demonstrate that our method can achieve 32% bit saving compared to the state-of-the-art method VQRF on multiple representative test datasets, with comparable training time.