qzhang95 / sts-cnn Goto Github PK

根据原论文

这里的spatial information按论文描述就是缺失部分的原图，也就是说输入了包括了残缺的影像和残缺的内容，那么我大胆的简化了一下

感觉直接简单的卷积就可以实现了

Hi,

In your paper you explained that loss function is the mean squared error. MSE between the residual mapping and is the other one the output from the model directly?

As stated in your paper, “For the dead lines in Aqua MODIS band 6, input y1 is the spectral data with missing information, and input y2 is the other intact spectral data as auxiliary information. For the ETM+ SLC-off problem, input y1 is the temporal image with missing information, and input y2 is another temporal image. For removing thick cloud in remote sensing imagery, input y1 is a temporal image with regions covered by thick cloud, and input y2 is another temporal image without cloud.”，why you fuse spatial,spectral,temporal features in this way? For example, for dead line, why you don't fuse temporal data and fuse spatial and spectral features only?