Aleth-NeRF: Low-light Condition View Synthesis with Concealing Fields

TL;DR

Aleth-NeRF is a novel approach that enhances low-light scene rendering by learning from dark images and introducing Concealing Fields, enabling unsupervised well-lit view synthesis and outperforming existing low-light enhancement methods.

Contribution

It proposes Aleth-NeRF, a method that models low-light scenes with Concealing Fields, allowing unsupervised rendering of well-lit views from dark images, and introduces a new paired multi-view low-light dataset.

Findings

Aleth-NeRF can render well-lit images from dark scenes.

It outperforms existing 2D low-light enhancement methods.

The method enables unsupervised learning of volumetric low-light scene representations.

Abstract

Common capture low-light scenes are challenging for most computer vision techniques, including Neural Radiance Fields (NeRF). Vanilla NeRF is viewer-centred simplifies the rendering process only as light emission from 3D locations in the viewing direction, thus failing to model the low-illumination induced darkness. Inspired by the emission theory of ancient Greeks that visual perception is accomplished by rays casting from eyes, we make slight modifications on vanilla NeRF to train on multiple views of low-light scenes, we can thus render out the well-lit scene in an unsupervised manner. We introduce a surrogate concept, Concealing Fields, that reduces the transport of light during the volume rendering stage. Specifically, our proposed method, Aleth-NeRF, directly learns from the dark image to understand volumetric object representation and concealing field under priors. By simply eliminating Concealing Fields, we can render a single or multi-view well-lit image(s) and gain superior performance over other 2D low-light enhancement methods. Additionally, we collect the first paired LOw-light and normal-light Multi-view (LOM) datasets for future research. This version is invalid, please refer to our new AAAI version: arXiv:2312.09093