1 code implementation • 30 Oct 2023 • Yi Xiao, Qiangqiang Yuan, Kui Jiang, Jiang He, Xianyu Jin, Liangpei Zhang
Recently, convolutional networks have achieved remarkable development in remote sensing image Super-Resoltuion (SR) by minimizing the regression objectives, e. g., MSE loss.
2 code implementations • 10 Apr 2023 • Yi Xiao, Qiangqiang Yuan, Kui Jiang, Xianyu Jin, Jiang He, Liangpei Zhang, Chia-Wen Lin
To explore the global dependency in the entire frame sequence, a Long-term Temporal Difference Module (L-TDM) is proposed, where the differences between forward and backward segments are incorporated and activated to guide the modulation of the temporal feature, leading to a holistic global compensation.