A Generative Model for Hallucinating Diverse Versions of Super Resolution Images
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 19 of its 21 references that are in the map. First posted on arXiv 12 Feb 2021.
Builds on
19 of 21 references.
References · 19
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2014Deep Learning Face Attributes in the Wildcited by 3,679
- 2016Improved Techniques for Training GANscited by 2,938
- 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
- 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
- 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
- 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
- 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
- 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
7 more
- 2017GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibriumcited by 208
- 2020Structure-Preserving Super Resolution with Gradient Guidancecited by 116
- 2019Diversity-Sensitive Conditional Generative Adversarial Networkscited by 77
- 2019Explorable Super Resolutioncited by 44
- 2020DeepSEE: Deep Disentangled Semantic Explorative Extreme Super-Resolutioncited by 17
- 2019MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networkscited by 14
- 2020Creating High Resolution Images with a Latent Adversarial Generatorcited by 8
Built on by
Citing papers per year: 2021: 1.
1 paper.