Skip to main content
Article
Low light image enhancement via global and local context modeling
arXiv
  • Aditya Arora, Inception Institute of Artificial Intelligence
  • Muhammad Haris, Mohamed bin Zayed University of Artificial Intelligence
  • Syed Waqas Zamir, Inception Institute of Artificial Intelligence
  • Munawar Hayat, Monash University. Australia
  • Fahad Shahbaz Khan, Mohamed bin Zayed University of Artificial Intelligence
  • Ling Shao, Inception Institute of Artificial Intelligence
  • Ming-Hsuan Yang, University of California & Google Research
Document Type
Article
Abstract

Images captured under low-light conditions manifest poor visibility, lack contrast and color vividness. Compared to conventional approaches, deep convolutional neural networks (CNNs) perform well in enhancing images. However, being solely reliant on confined fixed primitives to model dependencies, existing data-driven deep models do not exploit the contexts at various spatial scales to address low-light image enhancement. These contexts can be crucial towards inferring several image enhancement tasks, e.g., local and global contrast, brightness and color corrections; which requires cues from both local and global spatial extent. To this end, we introduce a context-aware deep network for low-light image enhancement. First, it features a global context module that models spatial correlations to find complementary cues over full spatial domain. Second, it introduces a dense residual block that captures local context with a relatively large receptive field. We evaluate the proposed approach using three challenging datasets: MIT-Adobe FiveK, LoL, and SID. On all these datasets, our method performs favorably against the state-of-the-arts in terms of standard image fidelity metrics. In particular, compared to the best performing method on the MIT-Adobe FiveK dataset, our algorithm improves PSNR from 23.04 dB to 24.45 dB. © 2021, CC BY-NC-SA.

DOI
doi.org/10.48550/arXiv.2101.00850
Publication Date
1-4-2021
Keywords
  • Computer Vision and Pattern Recognition (cs.CV)
Comments

Preprint: arXiv

Archived with thanks to arXiv

Preprint License: CC BY-NC-SA 4.0

Uploaded 25 March 2022

Citation Information
A. Arora, et. al., "Low light image enhancement via global and local context modeling" , 2021, arXiv:2101.00850