swz30 / MIRNet

[ECCV 2020] Learning Enriched Features for Real Image Restoration and Enhancement. SOTA results for image denoising, super-resolution, and image enhancement.
Other
667 stars 96 forks source link

Training Dataset link for Image Enhancement? #23

Open vztu opened 3 years ago

vztu commented 3 years ago

Hi thanks for your great work!

I sincerely appreciated that your MPRNet has provided all the training and val dataset download links. I am wondering could you also kindly provide the training and val datasets for RealSR, LOL, MIT-5K as well?

swz30 commented 3 years ago

Hi @vztu

RealSR: Please download version 1 from https://github.com/csjcai/RealSR

LOL: https://daooshee.github.io/BMVC2018website/

MIT-5K: Please download DNGs from https://data.csail.mit.edu/graphics/fivek/ and then follow this for data preparation https://github.com/nothinglo/Deep-Photo-Enhancer/issues/38

nanmehta commented 2 years ago

hi thanks for your nice work!

Can you please tell me do we need to train both on the LoL dataset and the FiveK dataset since Lol has PNG images and the Fivek dataset has JPEG images? Do we need to differently train on both datasets or we could make 1 dataset and combine it?