Affiliation:
1. School of Electronic and Electrical Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu 702-701, Republic of Korea
Abstract
High-dynamic-range (HDR) image synthesis is a technology developed to accurately reproduce the actual scene of an image on a display by extending the dynamic range of an image. Multi-exposure fusion (MEF) technology, which synthesizes multiple low-dynamic-range (LDR) images to create an HDR image, has been developed in various ways including pixel-based, patch-based, and deep learning-based methods. Recently, methods to improve the synthesis quality of images using deep-learning-based algorithms have mainly been studied in the field of MEF. Despite the various advantages of deep learning, deep-learning-based methods have a problem in that numerous multi-exposed and ground-truth images are required for training. In this study, we propose a self-supervised learning method that generates and learns reference images based on input images during the training process. In addition, we propose a method to train a deep learning model for an MEF with multiple tasks using dynamic hyperparameters on the loss functions. It enables effective network optimization across multiple tasks and high-quality image synthesis while preserving a simple network architecture. Our learning method applied to the deep learning model shows superior synthesis results compared to other existing deep-learning-based image synthesis algorithms.
Subject
General Mathematics,Engineering (miscellaneous),Computer Science (miscellaneous)
Reference36 articles.
1. Reinhard, E., Stark, M., Shirley, P., and Ferwerda, J. (2002, January 23–26). Photographic Tone Reproduction for Digital Images. Proceedings of the SIGGRAPH 2002: 29th Annual Conference on Computer Graphics and Interactive Techniques, San Antonio, TA, USA.
2. Tone-Mapping High Dynamic Range Images by Novel Histogram Adjustment;Duan;Pattern Recognit.,2010
3. Enhanced HDR Image Reproduction Using Gamma-Adaptation-Based Tone Compression and Detail-Preserved Blending;Jung;IEICE Trans. Fundam. Electron. Commun. Comput. Sci.,2020
4. Burt, P.J. (1984). The Pyramid as a Structure for Efficient Computation, Springer.
5. Multiple Exposure Fusion for High Dynamic Range Image Acquisition;Jinno;IEEE Trans. Image Process.,2012