Attention Guided Low-Light Image Enhancement with a Large Scale Low-Light Simulation Dataset

By Feifan Lv, Yu Li, Feng Lu. International Journal of Computer Vision, 2019

330 citations recorded by the source corpus.

Low-light image enhancement is challenging in that it needs to consider not only brightness recovery but also complex issues like color distortion and noise, which usually hide in the dark. Simply adjusting the brightness of a low-light image will inevitably amplify those artifacts. To address this difficult problem, this paper proposes a novel end-to-end attention-guided method based on multi-branch convolutional neural network. To this end, we first construct a synthetic dataset with carefully designed low-light simulation strategies. The dataset is much larger and more diverse than existing ones. With the new dataset for training, our method learns two attention maps to guide the brightness enhancement and denoising tasks respectively. The first attention map distinguishes underexposed regions from well lit regions, and the second attention map distinguishes noises from real textures. With their guidance, the proposed multi-branch decomposition-and-fusion enhancement network works in an input adaptive way. Moreover, a reinforcement-net further enhances color and contrast of the output image. Extensive experiments on multiple datasets demonstrate that our method can produce high fidelity enhancement results for low-light images and outperforms the current state-of-the-art methods by a large margin both quantitatively and visually.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/68dec8d0c97827ce1a943152e6620b8e300d568e

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Wenhan Yang
2. Xueyang Fu
3. Jianmin Jiang
4. Pingping Zhang
5. Wen-Bin Wu
6. Jian Weng
7. Xu Wang
8. Zhengjun Zha

In Media Technology

1. Wenhan Yang
2. Zhengjun Zha
3. Aiping Liu
4. Jianmin Jiang
5. Feng Wu
6. Jie Xiao
7. Pingping Zhang
8. Wen-Bin Wu

Citations in the corpus

• Image De-Raining Transformer (2022, background): “With the advent of the deep learning era [12], convolutional neural networks (CNNs) [13], [14], [15] have proven extremely successful for various low-level vision tasks [16], [17], [18], [19], [20].”
• URetinex-Net: Retinex-based Deep Unfolding Network for Low-light Image Enhancement (2022, methodology): “AGLLNet is a multi-branch CNN based architecture without Retinex-based setting, while apparently our proposed model outperforms it in all the metrics, which demonstrates the effectiveness of our Retinex-based unfolding strategy.”