Closed hhfzz closed 5 years ago
Hi. Tone-mapping is a quite different problem. I have seen some attempts at deep learning for this purpose, but I'm not sure how well-suited it is for this setup. The main problem is to specify the ground truth tone-mapped images, for which some tone-mapping method is needed. Then, if that method is already available, why use deep learning to mimic it? An alternative is to have a number of possible tone-mappings for each HDR image, and select as ground truth the one with best performance according to some measure (e.g. TMQI).
Thank you for your suggestion.
Hi gabrieleilertsen, I am very interested in this article. My research content is the tonal mapping algorithm of HDR images. I want to try to use the training model in this article to achieve the conversion from HDR images to LDR images.Do you have any ideas or Suggestions?thank you.