A Generative Model for Hallucinating Diverse Versions of Super Resolution Images

CoRR(2021)

引用 0|浏览3
暂无评分
摘要
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.
更多
查看译文
关键词
hallucinating diverse versions,generative model,resolution images,super
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要