tachikoma

Results 5 issues of tachikoma

Hi, I am using release version 1.1.2 and after switching glm from v0.9.9 to v0.9.9.8 and met following error: ` error: call to implicitly-deleted copy constructor of 'tmat4x4' (aka 'glm::mat')...

In Figure 1, the code GT is give, which is great. And the codeformer result looks pretty good too. Just asking, the training data for the codebook does not contains...

Does it means about only 27% code is correct matched (Top1) at level 1 degradation using codeformer?

Such as iteration and patch size, as what's done at https://yuantinghsieh.github.io/Image_Completion/ (but in matlab)

I thought both of them is calculated on separate color channel, what's the difference?