# Learning to See Low-Light Images via Feature Domain Adaptation

arXiv: https://arxiv.org/abs/2312.06723 · HTML: https://mlsanity.com/paper/2312.06723/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 71 references that are in the map.
- First posted on arXiv 11 Dec 2023.

## Builds on (most cited first, 30 of 42)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [EDVR: Video Restoration with Enhanced Deformable Convolutional Networks](https://mlsanity.com/paper/1905.02716/) (2019)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [Early Convolutions Help Transformers See Better](https://mlsanity.com/paper/2106.14881/) (2021)
- [Adversarial Domain Adaptation with Domain Mixup](https://mlsanity.com/paper/1912.01805/) (2019)
- [Neighborhood Attention Transformer](https://mlsanity.com/paper/2204.07143/) (2022)
- [Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernel](https://mlsanity.com/paper/1908.11775/) (2019)
- [A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising](https://mlsanity.com/paper/2003.12751/) (2020)
- [Zoom To Learn, Learn To Zoom](https://mlsanity.com/paper/1905.05169/) (2019)
- [DeepISP: Towards Learning an End-to-End Image Processing Pipeline](https://mlsanity.com/paper/1801.06724/) (2018)
- [Supervised Raw Video Denoising with a Benchmark Dataset on Dynamic Scenes](https://mlsanity.com/paper/2003.14013/) (2020)
- [Practical Deep Raw Image Denoising on Mobile Devices](https://mlsanity.com/paper/2010.06935/) (2020)
- [Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation](https://mlsanity.com/paper/2204.03838/) (2022)
- [A Comparative Study of Image Restoration Networks for General Backbone Network Design](https://mlsanity.com/paper/2310.11881/) (2023)
- [Image Demoireing with Learnable Bandpass Filters](https://mlsanity.com/paper/2004.00406/) (2020)
- [Abandoning the Bayer-Filter to See in the Dark](https://mlsanity.com/paper/2203.04042/) (2022)
- [CameraNet: A Two-Stage Framework for Effective Camera ISP Learning](https://mlsanity.com/paper/1908.01481/) (2019)
- [Domain Adaptation for Underwater Image Enhancement](https://mlsanity.com/paper/2108.09650/) (2021)
- [RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Image](https://mlsanity.com/paper/2309.02020/) (2023)
- [Towards Low Light Enhancement with RAW Images](https://mlsanity.com/paper/2112.14022/) (2021)
- [Towards Fast and Light-Weight Restoration of Dark Images](https://mlsanity.com/paper/2011.14133/) (2020)

## Built on by (most cited first, 8 of 8)

- [CWNet: Causal Wavelet Network for Low-Light Image Enhancement](https://mlsanity.com/paper/2507.10689/) (2025)
- [LLaPa: A Vision-Language Model Framework for Counterfactual-Aware Procedural Planning](https://mlsanity.com/paper/2507.08496/) (2025)
- [Learning Adaptive Lighting via Channel-Aware Guidance](https://mlsanity.com/paper/2412.01493/) (2024)
- [SAGE: A Visual Language Model for Anomaly Detection via Fact Enhancement and Entropy-aware Alignment](https://mlsanity.com/paper/2507.07939/) (2025)
- [DSDNet: Raw Domain Demoir'eing via Dual Color-Space Synergy](https://mlsanity.com/paper/2504.15756/) (2025)
- [Efficient RAW Image Deblurring with Adaptive Frequency Modulation](https://mlsanity.com/paper/2505.24407/) (2025)
- [Personalized Generative Low-light Image Denoising and Enhancement](https://mlsanity.com/paper/2412.14327/) (2024)
- [A Physically-Grounded Attack and Adaptive Defense Framework for Real-World Low-Light Image Enhancement](https://mlsanity.com/paper/2603.14304/) (2026)

## Abstract (arXiv)

Raw low light image enhancement (LLIE) has achieved much better performance than the sRGB domain enhancement methods due to the merits of raw data. However, the ambiguity between noisy to clean and raw to sRGB mappings may mislead the single-stage enhancement networks. The two-stage networks avoid ambiguity by decoupling the two mappings but usually have large computing complexity. To solve this problem, we propose a single-stage network empowered by Feature Domain Adaptation (FDA) to decouple the denoising and color mapping tasks in raw LLIE. The denoising encoder is supervised by the clean raw image, and then the denoised features are adapted for the color mapping task by an FDA module. We propose a Lineformer to serve as the FDA, which can well explore the global and local correlations with fewer line buffers (friendly to the line-based imaging process). During inference, the raw supervision branch is removed. In this way, our network combines the advantage of a two-stage enhancement process with the efficiency of single-stage inference. Experiments on four benchmark datasets demonstrate that our method achieves state-of-the-art performance with fewer computing costs (60% FLOPs of the two-stage method DNF). Our codes will be released after the acceptance of this work.