no code implementations • 14 Oct 2022 • Hanlin Wu, Ning Ni, Shan Wang, Libao Zhang
Besides, we introduce a degradation representation strategy based on contrastive learning to avoid the error amplification problem caused by the explicit degradation estimation.
1 code implementation • 14 Oct 2022 • Hanlin Wu, Ning Ni, Libao Zhang
We observe that the SR difficulty of different regions in an RSI varies greatly, and existing methods use the same deep network to process all regions in an image, resulting in a waste of computing resources.
1 code implementation • 29 Oct 2021 • Hanlin Wu, Ning Ni, Libao Zhang
To address the above problems, we propose a scale-aware dynamic network (SADN) for continuous-scale SR. First, we propose a scale-aware dynamic convolutional (SAD-Conv) layer for the feature learning of multiple SR tasks with various scales.