small ant

I calculate the fid score on deepfashion with your pretrained results, but the fid is 13.05, which is not consistent with yours. My fid calculation is based on the test...

 I have a question about your lpips score calculation. Should'nt lpips score is the lower the better? Does you adopt different metric calculation?

FID score

12

Do you calculate fid score by comparing the training set and the generated images ? I cannot reproduce the same fid in the paper. And which fid git repo you...

how to get the camera scale and translation from output of expose

1

- 

questions with inpainting input in inpaint_imagebart.py

1

 Should the input of first stage's vqgan encoder be the masked input? Because there should be no unmasked image in inference.

The metrics provided in NTED paper is inconsistent with the ones in GFLA

3

I note that the quantitative results in your new NTED paper is inconsistent with GFLA,can you explain this and point out the difference in your metrics calculation. NTED  GFLA...