# Noise Self-Regression: A New Learning Paradigm to Enhance Low-Light Images Without Task-Related Data

arXiv: https://arxiv.org/abs/2211.04700 · HTML: https://mlsanity.com/paper/2211.04700/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 54 references that are in the map.
- First posted on arXiv 9 Nov 2022.

## Builds on (most cited first, 27 of 27)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2001.05566/) (2020)
- [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)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [Deep Joint Rain Detection and Removal from a Single Image](https://mlsanity.com/paper/1609.07769/) (2016)
- [Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement](https://mlsanity.com/paper/2012.05609/) (2020)
- [LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement](https://mlsanity.com/paper/1511.03995/) (2015)
- [Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation](https://mlsanity.com/paper/2103.00860/) (2021)
- [Low-Light Image Enhancement with Normalizing Flow](https://mlsanity.com/paper/2109.05923/) (2021)
- [Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttime](https://mlsanity.com/paper/1810.02575/) (2018)
- [R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network](https://mlsanity.com/paper/2106.14501/) (2021)
- [Physics-based Noise Modeling for Extreme Low-light Photography](https://mlsanity.com/paper/2108.02158/) (2021)
- [Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection](https://mlsanity.com/paper/2205.03346/) (2022)
- [Semantically Contrastive Learning for Low-light Image Enhancement](https://mlsanity.com/paper/2112.06451/) (2021)
- [Dual Illumination Estimation for Robust Exposure Correction](https://mlsanity.com/paper/1910.13688/) (2019)
- [HLA-Face: Joint High-Low Adaptation for Low Light Face Detection](https://mlsanity.com/paper/2104.01984/) (2021)
- [Recurrent Exposure Generation for Low-Light Face Detection](https://mlsanity.com/paper/2007.10963/) (2020)
- [FCL-GAN: A Lightweight and Real-Time Baseline for Unsupervised Blind Image Deblurring](https://mlsanity.com/paper/2204.07820/) (2022)
- [Learn from Unpaired Data for Image Restoration: A Variational Bayes Approach](https://mlsanity.com/paper/2204.10090/) (2022)
- [LIME: A Method for Low-light IMage Enhancement](https://mlsanity.com/paper/1605.05034/) (2016)
- [D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration](https://mlsanity.com/paper/2207.03294/) (2022)

## Built on by (most cited first, 12 of 12)

- [Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image Restoration](https://mlsanity.com/paper/2504.09973/) (2025)
- [Towards Lightest Low-Light Image Enhancement Architecture for Mobile Devices](https://mlsanity.com/paper/2507.04277/) (2025)
- [LL-GaussianImage: Efficient Image Representation for Zero-shot Low-Light Enhancement with 2D Gaussian Splatting](https://mlsanity.com/paper/2601.15772/) (2026)
- [UltraFast-LiNET: Light-weight multi-scale shift convolutional network for real-time low-light image enhancement](https://mlsanity.com/paper/2512.02965/) (2025)
- [IGDNet: Zero-Shot Robust Underexposed Image Enhancement via Illumination-Guided and Denoising](https://mlsanity.com/paper/2507.02445/) (2025)
- [DST-Net: A Dual-Stream Transformer with Illumination-Independent Feature Guidance and Multi-Scale Spatial Convolution for Low-Light Image Enhancement](https://mlsanity.com/paper/2603.16482/) (2026)
- [Rethinking Low-Light Image Enhancement: A Log-Domain Intensity--Chromaticity Decoupling Perspective](https://mlsanity.com/paper/2605.02627/) (2026)
- [Continuous Splatting meets Retinex: Continuous Gaussian Splatting and Implicit Reflectance Modeling for Low-Light Image Enhancement](https://mlsanity.com/paper/2606.16159/) (2026)
- [Gaussian Light Field Splatting: A Physical Prior-Driven Vision Transformer for Unsupervised Low-Light Image Enhancement](https://mlsanity.com/paper/2606.17985/) (2026)
- [AIGS-Net: Compact Illumination Field Modeling via 2D Gaussian Splatting for Fast Low-Light Image Enhancement](https://mlsanity.com/paper/2606.17998/) (2026)
- [Learning Structural Illumination for Unsupervised Low-light Enhancement](https://mlsanity.com/paper/2608.08153/) (2026)
- [Di2CycleSB: Towards High-Quality Unsupervised Nighttime Visibility Enhancement via Schr"odinger Bridge Transformer](https://mlsanity.com/paper/2608.29043/) (2026)

## Abstract (arXiv)

Deep learning-based low-light image enhancement (LLIE) is a task of leveraging deep neural networks to enhance the image illumination while keeping the image content unchanged. From the perspective of training data, existing methods complete the LLIE task driven by one of the following three data types: paired data, unpaired data and zero-reference data. Each type of these data-driven methods has its own advantages, e.g., zero-reference data-based methods have very low requirements on training data and can meet the human needs in many scenarios. In this paper, we leverage pure Gaussian noise to complete the LLIE task, which further reduces the requirements for training data in LLIE tasks and can be used as another alternative in practical use. Specifically, we propose Noise SElf-Regression (NoiSER) without access to any task-related data, simply learns a convolutional neural network equipped with an instance-normalization layer by taking a random noise image, N(0,σ2) for each pixel, as both input and output for each training pair, and then the low-light image is fed to the trained network for predicting the normal-light image. Technically, an intuitive explanation for its effectiveness is as follows: 1) the self-regression reconstructs the contrast between adjacent pixels of the input image, 2) the instance-normalization layer may naturally remediate the overall magnitude/lighting of the input image, and 3) the N(0,σ2) assumption for each pixel enforces the output image to follow the well-known gray-world hypothesis when the image size is big enough. Compared to current state-of-the-art LLIE methods with access to different task-related data, NoiSER is highly competitive in enhancement quality, yet with a much smaller model size, and much lower training and inference cost. Besides, NoiSER also excels in mitigating overexposure and handling joint tasks.