search

xinntao / EDVR

Winning Solution in NTIRE19 Challenges on Video Restoration and Enhancement (CVPR19 Workshops) - Video Restoration with Enhanced Deformable Convolutional Networks. EDVR has been merged into BasicSR and this repo is a mirror of BasicSR.
https://github.com/xinntao/BasicSR
1.48k stars 320 forks source link

Question: Why are the results just image files? #159

Closed awan-10 closed 4 years ago

awan-10 commented 4 years ago

Thank you for sharing this great work. I have a naïve question about the results. I see that all the files in the results folders are images. Where is the result video? The same question about input video? Or is it just image based input and output and post-processing is done by the users themselves?

ckkelvinchan commented 4 years ago

Yes, this code only handles images. You need to manually transform a video into an image sequence and use the image sequence as an input. Similarly, you need to manually transform the output images into a video if you need a video format.

One possible way to do it is to use ffmpeg.