Lighting up NeRF via Unsupervised Decomposition and Enhancement

TL;DR

This paper introduces LLNeRF, an unsupervised method that jointly enhances low-light images and synthesizes high-quality novel views using a decomposed radiance field approach, overcoming limitations of existing methods.

Contribution

The paper proposes a novel unsupervised radiance field decomposition technique that enhances illumination and color correction during NeRF training from low-light images.

Findings

Outperforms existing low-light enhancement methods.

Produces high-quality, well-lit novel views with vivid colors.

Effectively reduces noise and corrects color distortion in low-light scenes.

Abstract

Neural Radiance Field (NeRF) is a promising approach for synthesizing novel views, given a set of images and the corresponding camera poses of a scene. However, images photographed from a low-light scene can hardly be used to train a NeRF model to produce high-quality results, due to their low pixel intensities, heavy noise, and color distortion. Combining existing low-light image enhancement methods with NeRF methods also does not work well due to the view inconsistency caused by the individual 2D enhancement process. In this paper, we propose a novel approach, called Low-Light NeRF (or LLNeRF), to enhance the scene representation and synthesize normal-light novel views directly from sRGB low-light images in an unsupervised manner. The core of our approach is a decomposition of radiance field learning, which allows us to enhance the illumination, reduce noise and correct the distorted colors jointly with the NeRF optimization process. Our method is able to produce novel view images with proper lighting and vivid colors and details, given a collection of camera-finished low dynamic range (8-bits/channel) images from a low-light scene. Experiments demonstrate that our method outperforms existing low-light enhancement methods and NeRF methods.