# DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision

arXiv: https://arxiv.org/abs/2309.06941 · HTML: https://mlsanity.com/paper/2309.06941/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 55 references that are in the map.
- First posted on arXiv 13 Sep 2023.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [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)
- [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)
- [Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues](https://mlsanity.com/paper/2007.09355/) (2020)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [FcaNet: Frequency Channel Attention Networks](https://mlsanity.com/paper/2012.11879/) (2020)
- [Getting to Know Low-light Images with The Exclusively Dark Dataset](https://mlsanity.com/paper/1805.11227/) (2018)
- [UG2+ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environments](https://mlsanity.com/paper/1904.04474/) (2019)
- [Debiased Contrastive Learning of Unsupervised Sentence Representations](https://mlsanity.com/paper/2205.00656/) (2022)
- [Wavelet-Based Dual-Branch Network for Image Demoireing](https://mlsanity.com/paper/2007.07173/) (2020)
- [SpectFormer: Frequency and Attention is what you need in a Vision Transformer](https://mlsanity.com/paper/2304.06446/) (2023)
- [STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation](https://mlsanity.com/paper/2302.01334/) (2023)
- [HLA-Face: Joint High-Low Adaptation for Low Light Face Detection](https://mlsanity.com/paper/2104.01984/) (2021)
- [DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation](https://mlsanity.com/paper/2011.09876/) (2020)
- [Wavelet Convolutional Neural Networks for Texture Classification](https://mlsanity.com/paper/1707.07394/) (2017)
- [GDIP: Gated Differentiable Image Processing for Object-Detection in Adverse Conditions](https://mlsanity.com/paper/2209.14922/) (2022)
- [LRT: An Efficient Low-Light Restoration Transformer for Dark Light Field Images](https://mlsanity.com/paper/2209.02197/) (2022)
- [PE-YOLO: Pyramid Enhancement Network for Dark Object Detection](https://mlsanity.com/paper/2307.10953/) (2023)
- [CamoFA: A Learnable Fourier-based Augmentation for Camouflage Segmentation](https://mlsanity.com/paper/2308.15660/) (2023)

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

- [Low-light Image Enhancement with Retinex Decomposition in Latent Space](https://mlsanity.com/paper/2603.15131/) (2026)

## Abstract (arXiv)

Low-light image enhancement restores the colors and details of a single image and improves high-level visual tasks. However, restoring the lost details in the dark area is still a challenge relying only on the RGB domain. In this paper, we delve into frequency as a new clue into the model and propose a DCT-driven enhancement transformer (DEFormer) framework. First, we propose a learnable frequency branch (LFB) for frequency enhancement contains DCT processing and curvature-based frequency enhancement (CFE) to represent frequency features. Additionally, we propose a cross domain fusion (CDF) to reduce the differences between the RGB domain and the frequency domain. Our DEFormer has achieved superior results on the LOL and MIT-Adobe FiveK datasets, improving the dark detection performance.