# Lighting up NeRF via Unsupervised Decomposition and Enhancement

arXiv: https://arxiv.org/abs/2307.10664 · HTML: https://mlsanity.com/paper/2307.10664/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 20 Jul 2023.

## Builds on (most cited first, 26 of 26)

- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021)
- [Depth-supervised NeRF: Fewer Views and Faster Training for Free](https://mlsanity.com/paper/2107.02791/) (2021)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [In-Place Scene Labelling and Understanding with Implicit Scene Representation](https://mlsanity.com/paper/2103.15875/) (2021)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images](https://mlsanity.com/paper/2111.13679/) (2021)
- [Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement](https://mlsanity.com/paper/2012.05609/) (2020)
- [Self-Calibrating Neural Radiance Fields](https://mlsanity.com/paper/2108.13826/) (2021)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo](https://mlsanity.com/paper/2109.01129/) (2021)
- [Low-Light Image Enhancement with Normalizing Flow](https://mlsanity.com/paper/2109.05923/) (2021)
- [Deblur-NeRF: Neural Radiance Fields from Blurry Images](https://mlsanity.com/paper/2111.14292/) (2021)
- [DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks](https://mlsanity.com/paper/1704.02470/) (2017)
- [HDR-NeRF: High Dynamic Range Neural Radiance Fields](https://mlsanity.com/paper/2111.14451/) (2021)
- [DeepLPF: Deep Local Parametric Filters for Image Enhancement](https://mlsanity.com/paper/2003.13985/) (2020)
- [T"oRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis](https://mlsanity.com/paper/2109.15271/) (2021)
- [Deep White-Balance Editing](https://mlsanity.com/paper/2004.01354/) (2020)
- [Distort-and-Recover: Color Enhancement using Deep Reinforcement Learning](https://mlsanity.com/paper/1804.04450/) (2018)
- [Image Correction via Deep Reciprocating HDR Transformation](https://mlsanity.com/paper/1804.04371/) (2018)

## Built on by (most cited first, 30 of 40)

- [Bilateral Guided Radiance Field Processing](https://mlsanity.com/paper/2406.00448/) (2024)
- [Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis](https://mlsanity.com/paper/2406.06216/) (2024)
- [Luminance-GS: Adapting 3D Gaussian Splatting to Challenging Lighting Conditions with View-Adaptive Curve Adjustment](https://mlsanity.com/paper/2504.01503/) (2025)
- [FruitNeRF: A Unified Neural Radiance Field based Fruit Counting Framework](https://mlsanity.com/paper/2408.06190/) (2024)
- [Gaussian in the Dark: Real-Time View Synthesis From Inconsistent Dark Images Using Gaussian Splatting](https://mlsanity.com/paper/2408.09130/) (2024)
- [RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstruction](https://mlsanity.com/paper/2512.23437/) (2025)
- [Radar Fields: Frequency-Space Neural Scene Representations for FMCW Radar](https://mlsanity.com/paper/2405.04662/) (2024)
- [I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions](https://mlsanity.com/paper/2510.22161/) (2025)
- [Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields](https://mlsanity.com/paper/2403.16224/) (2024)
- [LuSh-NeRF: Lighting up and Sharpening NeRFs for Low-light Scenes](https://mlsanity.com/paper/2411.06757/) (2024)
- [Color Shift Estimation-and-Correction for Image Enhancement](https://mlsanity.com/paper/2405.17725/) (2024)
- [LL-Gaussian: Low-Light Scene Reconstruction and Enhancement via Gaussian Splatting for Novel View Synthesis](https://mlsanity.com/paper/2504.10331/) (2025)
- [WeatherGS: 3D Scene Reconstruction in Adverse Weather Conditions via Gaussian Splatting](https://mlsanity.com/paper/2412.18862/) (2024)
- [Leveraging Thermal Modality to Enhance Reconstruction in Low-Light Conditions](https://mlsanity.com/paper/2403.14053/) (2024)
- [Neural Radiance Field-based Visual Rendering: A Comprehensive Review](https://mlsanity.com/paper/2404.00714/) (2024)
- [The NeRF Signature: Codebook-Aided Watermarking for Neural Radiance Fields](https://mlsanity.com/paper/2502.19125/) (2025)
- [Unifying Color and Lightness Correction with View-Adaptive Curve Adjustment for Robust 3D Novel View Synthesis](https://mlsanity.com/paper/2602.18322/) (2026)
- [Geometric-Aware Low-Light Image and Video Enhancement via Depth Guidance](https://mlsanity.com/paper/2312.15855/) (2023)
- [Low-Light Video Enhancement via Spatial-Temporal Consistent Decomposition](https://mlsanity.com/paper/2405.15660/) (2024)
- [LLGS: Unsupervised Gaussian Splatting for Image Enhancement and Reconstruction in Pure Dark Environment](https://mlsanity.com/paper/2503.18640/) (2025)
- [Gated Fields: Learning Scene Reconstruction from Gated Videos](https://mlsanity.com/paper/2405.19819/) (2024)
- [Robust Low-light Scene Restoration via Illumination Transition](https://mlsanity.com/paper/2507.03976/) (2025)
- [GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow Scenes](https://mlsanity.com/paper/2605.23602/) (2026)
- [Toward Robust and 3D-Aware RGB-NIR Imaging in the Dark](https://mlsanity.com/paper/2607.29684/) (2026)
- [Learning Novel View Synthesis from Heterogeneous Low-light Captures](https://mlsanity.com/paper/2403.13337/) (2024)
- [GAURA: Generalizable Approach for Unified Restoration and Rendering of Arbitrary Views](https://mlsanity.com/paper/2407.08221/) (2024)
- [Neural Active Structure-from-Motion in Dark and Textureless Environment](https://mlsanity.com/paper/2410.15378/) (2024)
- [Lumos3D: A Single-Forward Framework for Low-Light 3D Scene Restoration](https://mlsanity.com/paper/2511.09818/) (2025)
- [Beyond Darkness: Thermal-Supervised 3D Gaussian Splatting for Low-Light Novel View Synthesis](https://mlsanity.com/paper/2511.13011/) (2025)
- [SplatBright: Generalizable Low-Light Scene Reconstruction from Sparse Views via Physically-Guided Gaussian Enhancement](https://mlsanity.com/paper/2512.18655/) (2025)

## Abstract (arXiv)

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.