Log In Sign Up

A Generative Model for Hallucinating Diverse Versions of Super Resolution Images

by   Mohamed Abderrahmen Abid, et al.

Traditionally, the main focus of image super-resolution techniques is on recovering the most likely high-quality images from low-quality images, using a one-to-one low- to high-resolution mapping. Proceeding that way, we ignore the fact that there are generally many valid versions of high-resolution images that map to a given low-resolution image. We are tackling in this work the problem of obtaining different high-resolution versions from the same low-resolution image using Generative Adversarial Models. Our learning approach makes use of high frequencies available in the training high-resolution images for preserving and exploring in an unsupervised manner the structural information available within these images. Experimental results on the CelebA dataset confirm the effectiveness of the proposed method, which allows the generation of both realistic and diverse high-resolution images from low-resolution images.


page 3

page 4


To learn image super-resolution, use a GAN to learn how to do image degradation first

This paper is on image and face super-resolution. The vast majority of p...

Mapping Low-Resolution Images To Multiple High-Resolution Images Using Non-Adversarial Mapping

Several methods have recently been proposed for the Single Image Super-R...

ImagePairs: Realistic Super Resolution Dataset via Beam Splitter Camera Rig

Super Resolution is the problem of recovering a high-resolution image fr...

Super-resolution Guided Pore Detection for Fingerprint Recognition

Performance of fingerprint recognition algorithms substantially rely on ...

Label Super Resolution with Inter-Instance Loss

For the task of semantic segmentation, high-resolution (pixel-level) gro...

DEM Super-Resolution with EfficientNetV2

Efficient climate change monitoring and modeling rely on high-quality ge...

SuperVessel: Segmenting High-resolution Vessel from Low-resolution Retinal Image

Vascular segmentation extracts blood vessels from images and serves as t...