Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method

By Tao Wang, Kaihao Zhang, Tianrun Shen, Wenhan Luo, B. Stenger, Tong Lu. AAAI Conference on Artificial Intelligence, 2022

654 citations recorded by the source corpus.

As the quality of optical sensors improves, there is a need for processing large-scale images. In particular, the ability of devices to capture ultra-high definition (UHD) images and video places new demands on the image processing pipeline. In this paper, we consider the task of low-light image enhancement (LLIE) and introduce a large-scale database consisting of images at 4K and 8K resolution. We conduct systematic benchmarking studies and provide a comparison of current LLIE algorithms. As a second contribution, we introduce LLFormer, a transformer-based low-light enhancement method. The core components of LLFormer are the axis-based multi-head self-attention and cross-layer attention fusion block, which significantly reduces the linear complexity. Extensive experiments on the new dataset and existing public datasets show that LLFormer outperforms state-of-the-art methods. We also show that employing existing LLIE methods trained on our benchmark as a pre-processing step significantly improves the performance of downstream tasks, e.g., face detection in low-light conditions. The source code and pre-trained models are available at https://github.com/TaoWangzj/LLFormer.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/baf3d202261f1eb9122a157fc6480d93e2c3d03c