![]() Our model trained on HDR images ranked the first and CLHE was the runner-up. ![]() (20 participants and 20 images using pairwise comparisons) Our model trained on MIT-Adobe 5K dataset with unpaired dataĬycleGAN's model trained on our HDR dataset with unpaired dataĭPED's model trained on a specified device with paired data (supervised learning) Our model trained on MIT-Adobe 5K dataset with paired data (supervised learning) Our model trained on our HDR dataset with unpaired data Retouched by photographer from MIT-Adobe 5K dataset The A-WGAN part in the code did not implement decreasing the lambda since the initial lambda was relatively small in that case.) (The code was run on 0.12 version of TensorFlow. You can download the images according to the IDs. I am not sure whether I have right to release the HDR dataset we collected from Flickr so I put the ID of them. I directly used Lightroom to decode the images to TIF format and used Lightroom to resize the long side of the images to 512 resolution (The label images are from retoucher C). Regarding the data, I put the name of the images we used on MIT-Adobe FiveK dataset. There are a lot of unnecessary parts in the code. ![]() Therefore, I put my ugly code and the data here. There are too many people asked me to release the code even the code is not polished and is ugly as me. Data and Code (Supervsied and Unsupervised). If you use any code or data from our work, please cite our paper. TensorFlow implementation of the CVPR 2018 spotlight paper, Deep Photo Enhancer: Unpaired Learning for Image Enhancement from Photographs with GANs. Deep Photo Enhancer: Unpaired Learning for Image Enhancement from Photographs with GANs ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |