blurry inference result even if input video is 1080p about video-retalking HOT 21 OPEN

After a few days of hard work, I visualized every variable in the code by going through it line by line. The easiest way to do this is:
Lines 251-265 in [video-retalking/inference.py] are changed to the following code, which is commented in all other codes. This method does not compress the picture, but restorer.enhance method enhances the graphic.

          cropped_faces, restored_faces, restored_img = restorer.enhance(
               ff, has_aligned=False, only_center_face=True, paste_back=True)
           out.write(restored_img)

like this !

from video-retalking.

Thanks for pointing that out.
I will check the cause of this problem.

from video-retalking.

After a days of hard work, I debuged and traced the code by going through it line by line. i solved the issue by modifying only one-line code like belowed:

pp, orig_faces, enhanced_faces = enhancer.process(pp, xf, bbox=c, face_enhance=True, possion_blending=False) 

from video-retalking.

After a few days of hard work, I visualized every variable in the code by going through it line by line. The easiest way to do this is: Lines 251-265 in [video-retalking/inference.py] are changed to the following code, which is commented in all other codes. This method does not compress the picture, but restorer.enhance method enhances the graphic.

          cropped_faces, restored_faces, restored_img = restorer.enhance(
               ff, has_aligned=False, only_center_face=True, paste_back=True)
           out.write(restored_img)

like this !

清晰度问题确实得到了解决，但是人脸处会出现方框

from video-retalking.

I am experiencing the same problem. That's how it looks:

from video-retalking.

感謝您指出了這一點。 我會檢查這個問題的原因。

This happened to me too, and the surroundings became giant teeth, please help to solve the problem, thank you very much!

from video-retalking.

+1

from video-retalking.

The same problem

from video-retalking.

same here

from video-retalking.

me too

from video-retalking.

same here @kunncheng

from video-retalking.

me too，how to improve video

from video-retalking.

我这也一样，720P的片子都会碰到问题，希望可以帮助解决，谢谢

from video-retalking.

can your share result using that please, saves me reinstalling

from video-retalking.

經過幾天的努力，我將代碼中的每個變量逐行查看可視化。最簡單的方法是： 將 [video-retalking/inference.py] 中的第 251-265 行更改為以下代碼，該代碼在所有其他代碼中都有註釋。該方法不壓縮圖片，restorer.enhance方法是對圖片進行增強。

          cropped_faces, restored_faces, restored_img = restorer.enhance(
               ff, has_aligned=False, only_center_face=True, paste_back=True)
           out.write(restored_img)

像這樣 ！

Can you provide the installer, or provide the code so we can update it? Thank you!

from video-retalking.

After a few days of hard work, I visualized every variable in the code by going through it line by line. The easiest way to do this is: Lines 251-265 in [video-retalking/inference.py] are changed to the following code, which is commented in all other codes. This method does not compress the picture, but restorer.enhance method enhances the graphic.

          cropped_faces, restored_faces, restored_img = restorer.enhance(
               ff, has_aligned=False, only_center_face=True, paste_back=True)
           out.write(restored_img)

like this !

您好，我这边经过尝试，您提供的代码确实可以运行，但效果是：在人脸处会出现正方形。请问有办法改进吗？谢谢！

from video-retalking.

+1

from video-retalking.

+1

from video-retalking.

+1

from video-retalking.

After a days of hard work, I debuged and traced the code by going through it line by line. i solved the issue by modifying only one-line code like belowed:

pp, orig_faces, enhanced_faces = enhancer.process(pp, xf, bbox=c, face_enhance=True, possion_blending=False) 

I Appreciate your hard work going through the code line by line, did you find something which could make the inference for lip synthesis faster ?

from video-retalking.

After a days of hard work, I debuged and traced the code by going through it line by line. i solved the issue by modifying only one-line code like belowed:

pp, orig_faces, enhanced_faces = enhancer.process(pp, xf, bbox=c, face_enhance=True, possion_blending=False) 

Thank you! I can confirm this solves the issue of blurry output. But, I personally don't like the face enhancement as it is too aggressive and changes the original face too much. If you wish to avoid this result as well - leave face_enhace as "False" and just change possion_blending to "False". it still loses some of the original video's quality but the box around the face is solved.

from video-retalking.