Test: Clip vs. Non-clip

[Bonnie970]

Hi, Good job! I have been working on this paper as well. I found the same issue during test where there are obvious edge discontinuities at the clip borders! For the case where you did not use clip, did you just down-sample the original image to 320*320, and resize the alpha matte back to the original size? I found down-sample works pretty bad on high-resolution images :( Did you find a better way to run test on high-resolution images by any chance? Thank you.

[CDOTAD]

I just put the whole image into the generator for the non-clip case, and it could work in some cases. Except the clip or non-clip method, I also tried to padding the input to (n * 320, m * 320) with constant value like 0 for trimap. But the result was not so good as the original paper's. Maybe I didn't train the model well. My classmate suggested me to use sliding window on the input image, where the window size is 320*320 and the stride of it could be 200 * 200. Maybe you could try that method.