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.

翻译：神经辐射场（NeRF）是一种基于场景多视角图像及其对应相机位姿合成新颖视图的前沿方法。然而，在低光照场景中拍摄的图像由于像素强度低、噪声严重及颜色失真等问题，难以直接用于训练NeRF模型以生成高质量结果。将现有低光照图像增强方法与NeRF结合同样效果不佳，这是由于独立二维增强过程导致的视角不一致性。本文提出一种名为低光照NeRF（LLNeRF）的新方法，通过无监督方式直接从sRGB低光照图像中增强场景表征并合成正常光照新颖视图。该方法的核心是辐射场学习分解技术，能够在NeRF优化过程中同步实现光照增强、噪声抑制与颜色失真校正。实验表明，对于低光照场景下拍摄的相机完成型低动态范围（8位/通道）图像集合，本方法可生成具有合理光照、鲜艳色彩及丰富细节的新颖视图图像，且性能优于现有低光照增强方法与NeRF方法。