search

codyshen0000 / ITSRN

Code repo for "Implicit Transformer Network for Screen ContentImage Continuous Super-Resolution" (NeurIPS'21)
49 stars 7 forks source link

SCI1K-compression JPEG compression quality factor #4

Open Byeong-Hyun opened 2 years ago

Byeong-Hyun commented 2 years ago

Hi, I have a question about SCI1K-compression dataset.

Your paper stated that the quality factor of JPEG compression is randomly selected from 75, 85, and 95.

However, in wrappers.py and image_folder_compress.py, the code for quality factor is commented out as "qf = random.randrange(10, 75)".

I think that to follow the statement in paper, "qf = random.randrange(75, 96, 10)" is right code.

What code did you use for training and testing on SCI1K-compression?

codyshen0000 commented 2 years ago

I have tried to compress the image with lower quality, but the result was not good, so finally I use the quality factor 75, 85, and 95. When training, it is range from 75~95, when testing, it is randomly selected from 75, 85, and 95

Byeong-Hyun commented 2 years ago

Can you provide the quality factor code used for training and testing?