# Self-supervision via Controlled Transformation and Unpaired Self-conditioning for Low-light Image Enhancement

arXiv: https://arxiv.org/abs/2503.00642 · HTML: https://mlsanity.com/paper/2503.00642/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 66 references that are in the map.
- First posted on arXiv 1 Mar 2025.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [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)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement](https://mlsanity.com/paper/2012.05609/) (2020)
- [Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation](https://mlsanity.com/paper/2103.00860/) (2021)
- [Low-Light Image and Video Enhancement Using Deep Learning: A Survey](https://mlsanity.com/paper/2104.10729/) (2021)
- [A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising](https://mlsanity.com/paper/2003.12751/) (2020)
- [Low-light Image Enhancement via Breaking Down the Darkness](https://mlsanity.com/paper/2111.15557/) (2021)
- [Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement](https://mlsanity.com/paper/2110.00984/) (2021)
- [Self-supervised Image Enhancement Network: Training with Low Light Images Only](https://mlsanity.com/paper/2002.11300/) (2020)
- [Learning Deep Context-Sensitive Decomposition for Low-Light Image Enhancement](https://mlsanity.com/paper/2112.05147/) (2021)
- [Better Than Reference In Low Light Image Enhancement: Conditional Re-Enhancement Networks](https://mlsanity.com/paper/2008.11434/) (2020)
- [Unsupervised Low-light Image Enhancement with Decoupled Networks](https://mlsanity.com/paper/2005.02818/) (2020)

## Built on by (most cited first, 1 of 1)

- [Graph Your Own Prompt](https://mlsanity.com/paper/2509.23373/) (2025)

## Abstract (arXiv)

Real-world low-light images captured by imaging devices suffer from poor visibility and require a domain-specific enhancement to produce artifact-free outputs that reveal details. In this paper, we propose an unpaired low-light image enhancement network leveraging novel controlled transformation-based self-supervision and unpaired self-conditioning strategies. The model determines the required degrees of enhancement at the input image pixels, which are learned from the unpaired low-lit and well-lit images without any direct supervision. The self-supervision is based on a controlled transformation of the input image and subsequent maintenance of its enhancement in spite of the transformation. The self-conditioning performs training of the model on unpaired images such that it does not enhance an already-enhanced image or a well-lit input image. The inherent noise in the input low-light images is handled by employing low gradient magnitude suppression in a detail-preserving manner. In addition, our noise handling is self-conditioned by preventing the denoising of noise-free well-lit images. The training based on low-light image enhancement-specific attributes allows our model to avoid paired supervision without compromising significantly in performance. While our proposed self-supervision aids consistent enhancement, our novel self-conditioning facilitates adequate enhancement. Extensive experiments on multiple standard datasets demonstrate that our model, in general, outperforms the state-of-the-art both quantitatively and subjectively. Ablation studies show the effectiveness of our self-supervision and self-conditioning strategies, and the related loss functions.