Open AccessUCAN: A Learning-based Model to Enhance Poorly Exposed Images
Author(s) -
Lucas Ricardo Vieira Messias,
Cristiano Rafael Steffens,
Paulo L. J. Drews-Jr,
Silvia Botelho
Publication year - 2020
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/sibgrapi.est.2020.13004
Subject(s) - computer science , artificial intelligence , computer vision , process (computing) , image (mathematics) , image quality , image enhancement , contrast (vision) , range (aeronautics) , engineering , aerospace engineering , operating system
Image enhancement is a critical process in imagebased systems. In these systems, image quality is a crucial factor to achieve a good performance. Scenes with a dynamic range above the capability of the camera or poor lighting are challenging conditions, which usually result in low contrast images, and, with that, we can have the underexposure and/or overexposure problem. In this work, our aim is to restore illexposed images. For this purpose, we present UCAN, a small and fast learning-based model capable to restore and enhance poorly exposed images. The obtained results are evaluated using image quality indicators which show that the proposed network is able to improve images damaged by real and simulated exposure. Qualitative and quantitative results show that the proposed model outperforms the existing models for this objective.