WavePlanes: A compact Wavelet representation for Dynamic Neural Radiance Fields

Visual Information Laboratory, Univesity of Bristol
MY ALT TEXT

Model Overview: (a-f) illustrates the main pipeline, (1) outlines the compression pipeline (accomplished after training)

MY ALT TEXT

Abstract

Dynamic Neural Radiance Fields (Dynamic NeRF) enhance NeRF technology to model moving scenes. However, they are resource intensive and challenging to compress. To address this issue, this paper presents WavePlanes, a fast and more compact explicit model. We propose a multi-scale space and space-time feature plane representation using N-level 2-D wavelet coefficients. The inverse discrete wavelet transform reconstructs N feature signals at varying detail, which are linearly decoded to approximate the color and density of volumes in a 4-D grid. Exploiting the sparsity of wavelet coefficients, we compress a Hash Map containing only non-zero coefficients and their locations on each plane. This results in a compressed model size of ~12 MB. Compared with state-of-the-art plane-based models, WavePlanes is up to 15x smaller, less computationally demanding and achieves comparable results in as little as one hour of training - without requiring custom CUDA code or high performance computing resources. Additionally, we propose new feature fusion schemes that work as well as previously proposed schemes while providing greater interpretability.

Decomposing T-Rex Scene into Static and Dynamic Components

360 Degree view of Static Components

BibTeX

@article{azzarelli2023waveplanes,
        title={WavePlanes: A compact Wavelet representation for Dynamic Neural Radiance Fields},
        author={Azzarelli, Adrian and Anantrasirichai, Nantheera and Bull, David R},
        journal={arXiv preprint arXiv:2312.02218},
        year={2023}
      }