Computer Vision Foundation 2018

"Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors

Computer Vision Foundation 2018 yossigandelsman/DoubleDIP

It was shown [Ulyanov et al] that the structure of a single DIP generator network is sufficient to capture the low-level statistics of a single image.

IMAGE DEHAZING IMAGE INPAINTING JPEG ARTIFACT REMOVAL SEMANTIC SEGMENTATION TRANSPARENCY SEPARATION