Moreover, a noise-guidance data collection strategy is developed to address the training time consumption in multiple datasets optimization. Then we propose an exclusionary dual-learning strategy to address the feature diversity in perceptual- and L1- based cooperative learning. In this paper, we discuss the image types within a corrupted image and the property of perceptual- and Euclidean- based evaluation protocols. Although deep learning-based methods have achieved promising restoration quality on real-world image super-resolution datasets, they ignore the relationship between L1- and perceptual- minimization and roughly adopt auxiliary large-scale datasets for pre-training. Real-world image super-resolution is a practical image restoration problem that aims to obtain high-quality images from in-the-wild input, has recently received considerable attention with regard to its tremendous application potentials. Guangdong University of Technology, Sun Yat-sen University, Nanjing University of Science and Technology Hao Li, Jinghui Qin, Zhijing Yang, Pengxu Wei, Jinshan Pan, Liang Lin, Yukai Shi RWSR-EDL Real-World Super-Resolution by Exclusionary Dual-Learning (TMM 2022)
0 kommentar(er)
