Compressing Explicit Voxel Grid Representations: fast NeRFs become also small

TL;DR

Re:NeRF is a method that compresses explicit voxel grid-based NeRF models, reducing memory usage while maintaining performance, and is validated across multiple architectures and benchmarks.

Contribution

Re:NeRF introduces a novel compression technique for EVG-NeRFs, enabling smaller models without sacrificing rendering quality or speed.

Findings

Re:NeRF significantly reduces memory footprint of EVG-NeRFs.

Re:NeRF maintains comparable rendering performance.

Broad applicability across different EVG-NeRF architectures.

Abstract

NeRFs have revolutionized the world of per-scene radiance field reconstruction because of their intrinsic compactness. One of the main limitations of NeRFs is their slow rendering speed, both at training and inference time. Recent research focuses on the optimization of an explicit voxel grid (EVG) that represents the scene, which can be paired with neural networks to learn radiance fields. This approach significantly enhances the speed both at train and inference time, but at the cost of large memory occupation. In this work we propose Re:NeRF, an approach that specifically targets EVG-NeRFs compressibility, aiming to reduce memory storage of NeRF models while maintaining comparable performance. We benchmark our approach with three different EVG-NeRF architectures on four popular benchmarks, showing Re:NeRF's broad usability and effectiveness.