# ECAFormer: Low-light Image Enhancement using Cross Attention

arXiv: https://arxiv.org/abs/2406.13281 · HTML: https://mlsanity.com/paper/2406.13281/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 68 references that are in the map.
- First posted on arXiv 19 Jun 2024.

## Builds on (most cited first, 25 of 25)

- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [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)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020)
- [Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement](https://mlsanity.com/paper/2012.05609/) (2020)
- [Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement](https://mlsanity.com/paper/2303.06705/) (2023)
- [LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement](https://mlsanity.com/paper/1511.03995/) (2015)
- [Cross Attention Network for Few-shot Classification](https://mlsanity.com/paper/1910.07677/) (2019)
- [Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method](https://mlsanity.com/paper/2212.11548/) (2022)
- [Low-Light Image and Video Enhancement Using Deep Learning: A Survey](https://mlsanity.com/paper/2104.10729/) (2021)
- [LEDNet: Joint Low-light Enhancement and Deblurring in the Dark](https://mlsanity.com/paper/2202.03373/) (2022)
- [U-Net Transformer: Self and Cross Attention for Medical Image Segmentation](https://mlsanity.com/paper/2103.06104/) (2021)
- [ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement](https://mlsanity.com/paper/2107.05830/) (2021)
- [Learning Deep Context-Sensitive Decomposition for Low-Light Image Enhancement](https://mlsanity.com/paper/2112.05147/) (2021)
- [VTGNet: A Vision-based Trajectory Generation Network for Autonomous Vehicles in Urban Environments](https://mlsanity.com/paper/2004.12591/) (2020)
- [Let There be Light: Improved Traffic Surveillance via Detail Preserving Night-to-Day Transfer](https://mlsanity.com/paper/2105.05011/) (2021)
- [CuDi: Curve Distillation for Efficient and Controllable Exposure Adjustment](https://mlsanity.com/paper/2207.14273/) (2022)
- [PIE: Physics-inspired Low-light Enhancement](https://mlsanity.com/paper/2404.04586/) (2024)
- [TIDE: Test Time Few Shot Object Detection](https://mlsanity.com/paper/2311.18358/) (2023)

## Built on by (most cited first, 2 of 2)

- [From Noise to Nuance: Advances in Deep Generative Image Models](https://mlsanity.com/paper/2412.09656/) (2024)
- [Wavelet-based Decoupling Framework for low-light Stereo Image Enhancement](https://mlsanity.com/paper/2507.12188/) (2025)

## Abstract (arXiv)

Low-light image enhancement (LLIE) is critical in computer vision. Existing LLIE methods often fail to discover the underlying relationships between different sub-components, causing the loss of complementary information between multiple modules and network layers, ultimately resulting in the loss of image details. To beat this shortage, we design a hierarchical mutual Enhancement via a Cross Attention transformer (ECAFormer), which introduces an architecture that enables concurrent propagation and interaction of multiple features. The model preserves detailed information by introducing a Dual Multi-head self-attention (DMSA), which leverages visual and semantic features across different scales, allowing them to guide and complement each other. Besides, a Cross-Scale DMSA block is introduced to capture the residual connection, integrating cross-layer information to further enhance image detail. Experimental results show that ECAFormer reaches competitive performance across multiple benchmarks, yielding nearly a 3% improvement in PSNR over the suboptimal method, demonstrating the effectiveness of information interaction in LLIE.