UEGAN
UEGAN copied to clipboard
About the dataset
Dear,
I appreciate your great work!
I am quite curious about the dataset because preparing dataset for unsupervised learning is not an easy task (to define 'low-quality' and 'high-quality' image). Could you provide your dataset? You can send via email: [email protected]
Thank you so much.
For the MIT-Adobe FiveK dataset, I directly used Lightroom to decode the images to png format and resized the short side of the images to 512 resolution. The 'low-quality' images are captured raw images and 'high-quality' images are from expert C. You can download the images used in our work from the following links: https://drive.google.com/drive/folders/1Jv0_9CnYxh_2ReFaVrwG19O3F7xBtdZT?usp=sharing
For the Flickr dataset, I am not sure whether I have the right to release it so you need to collect/crawl it by yourself.
Thanks.
Thank you so much! Hope that you could public flickr if possible!
@eezkni Hello, what's dataset you train the 'identity loss' ? Flickr dataset you mentioned in your paper? Thank you.
@ComingPeopleHW Both the MIT-Adobe FiveK dataset and Flickr dataset used the 'identity loss'. If you have any further questions, feel free to contact me via email ([email protected]).
Hi @eezkni , After reading your paper, I have three questions:
- Could you explain how high-quality input can help the generator generate correct image?
- When you train your model, do you only feed the images generated from degraded images into discriminator or you also use the images generated from high-quality ones?
- What is your multi-scale discriminator's output? feature maps? scalar value?
Thank you