Super-Resolution via Conditional Implicit Maximum Likelihood Estimation
arXiv:1810.01406
Abstract
Single-image super-resolution (SISR) is a canonical problem with diverse applications. Leading methods like SRGAN produce images that contain various artifacts, such as high-frequency noise, hallucinated colours and shape distortions, which adversely affect the realism of the result. In this paper, we propose an alternative approach based on an extension of the method of Implicit Maximum Likelihood Estimation (IMLE). We demonstrate greater effectiveness at noise reduction and preservation of the original colours and shapes, yielding more realistic super-resolved images.
arXiv comment12 pages, 7 figures
References in corpus (6)
- Do GANs actually learn the distribution? An empirical study
- On distinguishability criteria for estimating generative models
- Super-Resolution with Deep Convolutional Sufficient Statistics
- Implicit Maximum Likelihood Estimation
- Likelihood-free inference via classification
- Fast k-Nearest Neighbour Search via Prioritized DCI