m-tassano / fastdvdnet

FastDVDnet: A Very Fast Deep Video Denoising algorithm
MIT License
572 stars 123 forks source link

How to generate video according to images to compute ST-RRED #42

Closed huanzheng551803 closed 2 years ago

huanzheng551803 commented 2 years ago

I have tried my best to convert images to videos. But the resulted videos plus the st-rred computation code you have given in issue gives a lower strred. Can you share your code about how to conver result imges to videos and then compute st-rred?

gulzainali98 commented 2 years ago

need this @m-tassano

m-tassano commented 2 years ago

As I replied to Huan by email, I basically use the vread function from skvideo, for example

refseq = vread(seq_ref_path, num_frames=nframes, outputdict={"-pix_fmt": "gray"})