# Semantically Contrastive Learning for Low-light Image Enhancement

arXiv: https://arxiv.org/abs/2112.06451 · HTML: https://mlsanity.com/paper/2112.06451/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 40 references that are in the map.
- First posted on arXiv 13 Dec 2021.

## Builds on (most cited first, 23 of 23)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [In Defense of the Triplet Loss for Person Re-Identification](https://mlsanity.com/paper/1703.07737/) (2017)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Data-Efficient Image Recognition with Contrastive Predictive Coding](https://mlsanity.com/paper/1905.09272/) (2019)
- [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)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](https://mlsanity.com/paper/1711.07064/) (2017)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [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)
- [Contrastive Learning for Compact Single Image Dehazing](https://mlsanity.com/paper/2104.09367/) (2021)
- [DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks](https://mlsanity.com/paper/1704.02470/) (2017)
- [Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild](https://mlsanity.com/paper/2005.13983/) (2020)

## Built on by (most cited first, 30 of 31)

- [Low-Light Image Enhancement via Structure Modeling and Guidance](https://mlsanity.com/paper/2305.05839/) (2023)
- [Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bank](https://mlsanity.com/paper/2303.09101/) (2023)
- [Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement](https://mlsanity.com/paper/2304.07039/) (2023)
- [SGUIE-Net: Semantic Attention Guided Underwater Image Enhancement with Multi-Scale Perception](https://mlsanity.com/paper/2201.02832/) (2022)
- [Bilevel Fast Scene Adaptation for Low-Light Image Enhancement](https://mlsanity.com/paper/2306.01343/) (2023)
- [Improving Lens Flare Removal with General Purpose Pipeline and Multiple Light Sources Recovery](https://mlsanity.com/paper/2308.16460/) (2023)
- [Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancement](https://mlsanity.com/paper/2203.04814/) (2022)
- [Supervised Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2209.00078/) (2022)
- [Noise Self-Regression: A New Learning Paradigm to Enhance Low-Light Images Without Task-Related Data](https://mlsanity.com/paper/2211.04700/) (2022)
- [CF-YOLO: Cross Fusion YOLO for Object Detection in Adverse Weather with a High-quality Real Snow Dataset](https://mlsanity.com/paper/2206.01381/) (2022)
- [Unsupervised Deraining: Where Asymmetric Contrastive Learning Meets Self-similarity](https://mlsanity.com/paper/2211.00837/) (2022)
- [PIE: Physics-inspired Low-light Enhancement](https://mlsanity.com/paper/2404.04586/) (2024)
- [Detail-recovery Image Deraining via Dual Sample-augmented Contrastive Learning](https://mlsanity.com/paper/2204.02772/) (2022)
- [Priors in Deep Image Restoration and Enhancement: A Survey](https://mlsanity.com/paper/2206.02070/) (2022)
- [ALL-E: Aesthetics-guided Low-light Image Enhancement](https://mlsanity.com/paper/2304.14610/) (2023)
- [DEANet: Decomposition Enhancement and Adjustment Network for Low-Light Image Enhancement](https://mlsanity.com/paper/2209.06823/) (2022)
- [SLLEN: Semantic-aware Low-light Image Enhancement Network](https://mlsanity.com/paper/2211.11571/) (2022)
- [ClassLIE: Structure- and Illumination-Adaptive Classification for Low-Light Image Enhancement](https://mlsanity.com/paper/2312.13265/) (2023)
- [Boosting HDR Image Reconstruction via Semantic Knowledge Transfer](https://mlsanity.com/paper/2503.15361/) (2025)
- [ReF-LLE: Personalized Low-Light Enhancement via Reference-Guided Deep Reinforcement Learning](https://mlsanity.com/paper/2506.22216/) (2025)
- [Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement](https://mlsanity.com/paper/2511.01510/) (2025)
- [Semi-LLIE: Semi-supervised Contrastive Learning with Mamba-based Low-light Image Enhancement](https://mlsanity.com/paper/2409.16604/) (2024)
- [Hierarchical Semantic-Visual Fusion of Visible and Near-infrared Images for Long-range Haze Removal](https://mlsanity.com/paper/2507.03893/) (2025)
- [DeshadowMamba: Deshadowing as 1D Sequential Similarity](https://mlsanity.com/paper/2510.24260/) (2025)
- [When A Conventional Filter Meets Deep Learning: Basis Composition Learning on Image Filters](https://mlsanity.com/paper/2203.00258/) (2022)
- [Preventing Dimensional Collapse of Incomplete Multi-View Clustering via Direct Contrastive Learning](https://mlsanity.com/paper/2303.12241/) (2023)
- [Poisson Informed Retinex Network for Extreme Low-Light Image Enhancement](https://mlsanity.com/paper/2506.04470/) (2025)
- [Self-DACE++: Robust Low-Light Enhancement via Efficient Adaptive Curve Estimation](https://mlsanity.com/paper/2604.25367/) (2026)
- [Rethinking Low-Light Image Enhancement: A Log-Domain Intensity--Chromaticity Decoupling Perspective](https://mlsanity.com/paper/2605.02627/) (2026)
- [Thresholded Cross-Attention for Reliable Intensity-Chromaticity Fusion in Low-Light Image Enhancement](https://mlsanity.com/paper/2607.13925/) (2026)

## Abstract (arXiv)

Low-light image enhancement (LLE) remains challenging due to the unfavorable prevailing low-contrast and weak-visibility problems of single RGB images. In this paper, we respond to the intriguing learning-related question -- if leveraging both accessible unpaired over/underexposed images and high-level semantic guidance, can improve the performance of cutting-edge LLE models? Here, we propose an effective semantically contrastive learning paradigm for LLE (namely SCL-LLE). Beyond the existing LLE wisdom, it casts the image enhancement task as multi-task joint learning, where LLE is converted into three constraints of contrastive learning, semantic brightness consistency, and feature preservation for simultaneously ensuring the exposure, texture, and color consistency. SCL-LLE allows the LLE model to learn from unpaired positives (normal-light)/negatives (over/underexposed), and enables it to interact with the scene semantics to regularize the image enhancement network, yet the interaction of high-level semantic knowledge and the low-level signal prior is seldom investigated in previous methods. Training on readily available open data, extensive experiments demonstrate that our method surpasses the state-of-the-arts LLE models over six independent cross-scenes datasets. Moreover, SCL-LLE's potential to benefit the downstream semantic segmentation under extremely dark conditions is discussed. Source Code: https://github.com/LingLIx/SCL-LLE.