why use "-flow" when compute non-occlusion mask?
Hi,
Thanks for releasing code! I have a question about optical flow. Why you use "-flow" instead of "flow" in the warping function?

Thanks for your interest. E.g. The flow is computed based on Img1 -> Img2, if we want to warp back from Img2 to Img1 pixel by pixel. We need to use the reverse flow from Img2 -> Img1.
Thanks for your interest. E.g. The flow is computed based on Img1 -> Img2, if we want to warp back from Img2 to Img1 pixel by pixel. We need to use the reverse flow from Img2 -> Img1.
Hi, As you mentioned, flow is computed based on Img1 -> Img2 but what we need is the flow from Img2 -> Img1. My concern is that does the -flow equals to the flow from Img2 -> Img1?
Thanks!