Compressing Volumetric Radiance Fields to 1 MB

11/29/2022
by   Lingzhi Li, et al.
0

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× 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 <https://github.com/AlgoHunt/VQRF>

READ FULL TEXT

page 7

page 8

page 12

page 13

page 14

page 15

research
05/29/2023

Compact Real-time Radiance Fields with Neural Codebook

Reconstructing neural radiance fields with explicit volumetric represent...
research
06/15/2022

Variable Bitrate Neural Fields

Neural approximations of scalar and vector fields, such as signed distan...
research
12/18/2022

Masked Wavelet Representation for Compact Neural Radiance Fields

Neural radiance fields (NeRF) have demonstrated the potential of coordin...
research
10/26/2022

Streaming Radiance Fields for 3D Video Synthesis

We present an explicit-grid based method for efficiently reconstructing ...
research
07/16/2023

Adaptively Placed Multi-Grid Scene Representation Networks for Large-Scale Data Visualization

Scene representation networks (SRNs) have been recently proposed for com...
research
08/25/2022

LightAMR format standard and lossless compression algorithms for adaptive mesh refinement grids: RAMSES use case

The evolution of parallel I/O library as well as new concepts such as 'i...
research
08/19/2020

Deep Volumetric Ambient Occlusion

We present a novel deep learning based technique for volumetric ambient ...

Please sign up or login with your details

Forgot password? Click here to reset