Super-Resolution via Conditional Implicit Maximum Likelihood Estimation
This addresses artifact issues in super-resolution for applications requiring high-quality image enhancement, but it appears incremental as it builds on existing methods.
The paper tackles the problem of artifacts in single-image super-resolution by proposing a method based on Conditional Implicit Maximum Likelihood Estimation, which reduces noise and preserves colors and shapes to yield more realistic images.
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.