Bright-NeRF:Brightening Neural Radiance Field with Color Restoration from Low-light Raw Images

TL;DR

Bright-NeRF introduces an unsupervised method to learn high-quality neural radiance fields from low-light raw images, enabling effective color restoration, denoising, and novel view synthesis in challenging lighting conditions.

Contribution

The paper presents a novel approach that combines a physically-inspired sensor response model with a chromatic adaptation loss to improve scene representation from low-light raw images.

Findings

Outperforms existing 2D and 3D methods in low-light conditions

Effectively restores color and reduces noise in low-light images

Enables high-quality novel view synthesis from challenging data

Abstract

Neural Radiance Fields (NeRFs) have demonstrated prominent performance in novel view synthesis. However, their input heavily relies on image acquisition under normal light conditions, making it challenging to learn accurate scene representation in low-light environments where images typically exhibit significant noise and severe color distortion. To address these challenges, we propose a novel approach, Bright-NeRF, which learns enhanced and high-quality radiance fields from multi-view low-light raw images in an unsupervised manner. Our method simultaneously achieves color restoration, denoising, and enhanced novel view synthesis. Specifically, we leverage a physically-inspired model of the sensor's response to illumination and introduce a chromatic adaptation loss to constrain the learning of response, enabling consistent color perception of objects regardless of lighting conditions. We further utilize the raw data's properties to expose the scene's intensity automatically. Additionally, we have collected a multi-view low-light raw image dataset to advance research in this field. Experimental results demonstrate that our proposed method significantly outperforms existing 2D and 3D approaches. Our code and dataset will be made publicly available.