ltkong218 / waveletvfi Goto Github PK

Hi there, I was intrigued reading your work and thought the idea of using a wavelet transform was interesting. I have a question about the methodology you use to obtain the motion magnitude values you present in Table V/Fig.11
When you use a flow network to estimate the flow you get a tensor in the shape (batch, 2, h, w). To find the mean over the entire set, do you find the mean for each flow tensor e.g. torch.mean(flow) and then do that for each input image. Or do you do something else like concatenating the tensors and then finding the mean along the dimension of concatenation?

Thanks