Avinash Paliwal

@ag14774 The published code can be run on the test scenes provided that have already been pre-processed - homography transformation and color matching using [NRDC](https://www.cse.huji.ac.il/~yoavhacohen/nrdc/). To align the video frames,...

Hey @women1995. It looks like all the pages from the author were removed from the domain. I can share the file with you.

Is this during training or eval?

I don't think we can do much for resolutions above 1080p. Since there are two CNNs, we can run the first CNN, generate the intermediate outputs and then run the...

@Thomasedv . You are right. I have used it in some other pyTorch code and though it fixes the memory issue, it also makes the eval slower. I can add...

I will add a colab version for evaluation. It will take some time.

Thanks for pointing this out. I will add the padding logic shortly. > The reverse normalization does not give the same result. Can you elaborate more on this issue? And...

I don't understand why the normalization would cause artifacts. In the implementation, it's just subtraction and addition of a constant from the image. Well anyway I can change the implementation...

> you know the color is stored as 0-255 integers, and when you do normalization and reverse, it may cause some small difference. Maybe you can test more about this....

Hi @Zhang-Jing-Xuan. Unfortunately, I cannot share the training dataset since the videos are not under the Creative Commons license.