Compressing Volumetric Radiance Fields to 1 MB

TL;DR

This paper introduces VQRF, a framework that significantly compresses volumetric radiance fields to 1 MB with minimal quality loss, enabling efficient storage and real-time rendering.

Contribution

The paper proposes a novel compression framework combining voxel pruning and trainable vector quantization for volumetric radiance fields.

Findings

Achieves 100× compression ratio reducing model size to 1 MB.

Maintains high visual quality with negligible loss after compression.

Demonstrates strong generalization across different volumetric methods.

Abstract

Approximating radiance fields with volumetric grids is one of promising directions for improving NeRF, represented by methods like Plenoxels and DVGO, which achieve super-fast training convergence and real-time rendering. However, these methods typically require a tremendous storage overhead, costing up to hundreds of megabytes of disk space and runtime memory for a single scene. We address this issue in this paper by introducing a simple yet effective framework, called vector quantized radiance fields (VQRF), for compressing these volume-grid-based radiance fields. We first present a robust and adaptive metric for estimating redundancy in grid models and performing voxel pruning by better exploring intermediate outputs of volumetric rendering. A trainable vector quantization is further proposed to improve the compactness of grid models. In combination with an efficient joint tuning strategy and post-processing, our method can achieve a compression ratio of 100$\times$ by reducing the overall model size to 1 MB with negligible loss on visual quality. Extensive experiments demonstrate that the proposed framework is capable of achieving unrivaled performance and well generalization across multiple methods with distinct volumetric structures, facilitating the wide use of volumetric radiance fields methods in real-world applications. Code Available at \url{https://github.com/AlgoHunt/VQRF}