# Learning Deep Context-Sensitive Decomposition for Low-Light Image Enhancement arXiv: https://arxiv.org/abs/2112.05147 ยท HTML: https://mlsanity.com/paper/2112.05147/ ## Key facts - Cited by 23 papers in the map (data through 14 Oct 2026). - Builds on 24 of its 63 references that are in the map. - First posted on arXiv 9 Dec 2021. ## Builds on (most cited first, 24 of 24) - [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015) - [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016) - [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016) - [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) - [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018) - [Unsupervised Image-to-Image Translation Networks](https://mlsanity.com/paper/1703.00848/) (2017) - [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019) - [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018) - [Deep Learning for Generic Object Detection: A Survey](https://mlsanity.com/paper/1809.02165/) (2018) - [Toward Convolutional Blind Denoising of Real Photographs](https://mlsanity.com/paper/1807.04686/) (2018) - [LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement](https://mlsanity.com/paper/1511.03995/) (2015) - [Deblurring by Realistic Blurring](https://mlsanity.com/paper/2004.01860/) (2020) - [Getting to Know Low-light Images with The Exclusively Dark Dataset](https://mlsanity.com/paper/1805.11227/) (2018) - [Context Prior for Scene Segmentation](https://mlsanity.com/paper/2004.01547/) (2020) - [Domain Adaptation for Image Dehazing](https://mlsanity.com/paper/2005.04668/) (2020) - [Denoising Prior Driven Deep Neural Network for Image Restoration](https://mlsanity.com/paper/1801.06756/) (2018) - [A General Decoupled Learning Framework for Parameterized Image Operators](https://mlsanity.com/paper/1907.05852/) (2019) - [Exposure: A White-Box Photo Post-Processing Framework](https://mlsanity.com/paper/1709.09602/) (2017) - [Two-Stream Action Recognition-Oriented Video Super-Resolution](https://mlsanity.com/paper/1903.05577/) (2019) - [Learning Converged Propagations with Deep Prior Ensemble for Image Enhancement](https://mlsanity.com/paper/1810.04012/) (2018) - [State-aware Anti-drift Robust Correlation Tracking](https://mlsanity.com/paper/1806.10759/) (2018) - [Unified Single-Image and Video Super-Resolution via Denoising Algorithms](https://mlsanity.com/paper/1810.01938/) (2018) - [Low-light Image Enhancement Algorithm Based on Retinex and Generative Adversarial Network](https://mlsanity.com/paper/1906.06027/) (2019) ## Built on by (most cited first, 23 of 23) - [Target-aware Dual Adversarial Learning and a Multi-scenario Multi-Modality Benchmark to Fuse Infrared and Visible for Object Detection](https://mlsanity.com/paper/2203.16220/) (2022) - [An Interactively Reinforced Paradigm for Joint Infrared-Visible Image Fusion and Saliency Object Detection](https://mlsanity.com/paper/2305.09999/) (2023) - [Bilevel Fast Scene Adaptation for Low-Light Image Enhancement](https://mlsanity.com/paper/2306.01343/) (2023) - [Empowering Low-Light Image Enhancer through Customized Learnable Priors](https://mlsanity.com/paper/2309.01958/) (2023) - [Low-light Image Enhancement by Retinex Based Algorithm Unrolling and Adjustment](https://mlsanity.com/paper/2202.05972/) (2022) - [Hybrid-Supervised Dual-Search: Leveraging Automatic Learning for Loss-free Multi-Exposure Image Fusion](https://mlsanity.com/paper/2309.01113/) (2023) - [Spatial-frequency Dual-Domain Feature Fusion Network for Low-Light Remote Sensing Image Enhancement](https://mlsanity.com/paper/2404.17400/) (2024) - [Retinex Image Enhancement Based on Sequential Decomposition With a Plug-and-Play Framework](https://mlsanity.com/paper/2210.05436/) (2022) - [Practical exposure correction via compensation](https://mlsanity.com/paper/2212.14245/) (2022) - [LMT-GP: Combined Latent Mean-Teacher and Gaussian Process for Semi-supervised Low-light Image Enhancement](https://mlsanity.com/paper/2408.16235/) (2024) - [IGDNet: Zero-Shot Robust Underexposed Image Enhancement via Illumination-Guided and Denoising](https://mlsanity.com/paper/2507.02445/) (2025) - [Self-Reference Deep Adaptive Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2308.08197/) (2023) - [AoSRNet: All-in-One Scene Recovery Networks via Multi-knowledge Integration](https://mlsanity.com/paper/2402.03738/) (2024) - [Trash to Treasure: Low-Light Object Detection via Decomposition-and-Aggregation](https://mlsanity.com/paper/2309.03548/) (2023) - [CodeEnhance: A Codebook-Driven Approach for Low-Light Image Enhancement](https://mlsanity.com/paper/2404.05253/) (2024) - [ECAFormer: Low-light Image Enhancement using Cross Attention](https://mlsanity.com/paper/2406.13281/) (2024) - [Self-supervision via Controlled Transformation and Unpaired Self-conditioning for Low-light Image Enhancement](https://mlsanity.com/paper/2503.00642/) (2025) - [Random Weights Networks Work as Loss Prior Constraint for Image Restoration](https://mlsanity.com/paper/2303.16438/) (2023) - [Diving into Darkness: A Dual-Modulated Framework for High-Fidelity Super-Resolution in Ultra-Dark Environments](https://mlsanity.com/paper/2309.05267/) (2023) - [Joint Correcting and Refinement for Balanced Low-Light Image Enhancement](https://mlsanity.com/paper/2309.16128/) (2023) - [Edge-guided Low-light Image Enhancement with Inertial Bregman Alternating Linearized Minimization](https://mlsanity.com/paper/2403.01142/) (2024) - [Natural Language Supervision for Low-light Image Enhancement](https://mlsanity.com/paper/2501.06546/) (2025) - [A review of advancements in low-light image enhancement using deep learning](https://mlsanity.com/paper/2505.05759/) (2025) ## Abstract (arXiv) Enhancing the quality of low-light images plays a very important role in many image processing and multimedia applications. In recent years, a variety of deep learning techniques have been developed to address this challenging task. A typical framework is to simultaneously estimate the illumination and reflectance, but they disregard the scene-level contextual information encapsulated in feature spaces, causing many unfavorable outcomes, e.g., details loss, color unsaturation, artifacts, and so on. To address these issues, we develop a new context-sensitive decomposition network architecture to exploit the scene-level contextual dependencies on spatial scales. More concretely, we build a two-stream estimation mechanism including reflectance and illumination estimation network. We design a novel context-sensitive decomposition connection to bridge the two-stream mechanism by incorporating the physical principle. The spatially-varying illumination guidance is further constructed for achieving the edge-aware smoothness property of the illumination component. According to different training patterns, we construct CSDNet (paired supervision) and CSDGAN (unpaired supervision) to fully evaluate our designed architecture. We test our method on seven testing benchmarks to conduct plenty of analytical and evaluated experiments. Thanks to our designed context-sensitive decomposition connection, we successfully realized excellent enhanced results, which fully indicates our superiority against existing state-of-the-art approaches. Finally, considering the practical needs for high-efficiency, we develop a lightweight CSDNet (named LiteCSDNet) by reducing the number of channels. Further, by sharing an encoder for these two components, we obtain a more lightweight version (SLiteCSDNet for short). SLiteCSDNet just contains 0.0301M parameters but achieves the almost same performance as CSDNet.