Generating Unobserved Alternatives: A Case Study through Super-Resolution and Decompression

Shichong Peng, Ke Li

Keywords: one-to-many prediction, generative models

Abstract: In this paper, we consider problems where multiple predictions can be considered correct, but only one of them is given as supervision. This setting differs from both the regression and class-conditional generative modelling settings: in the former, there is a unique ground truth for each input, which is provided as supervision; in the latter, there are many ground truths for each input, and many are provided as supervision. Applying either regression methods and conditional generative models to the setting considered in this paper often results in a model that can only make a single prediction for each input. We explore several problems that have this property, which naturally arise in image processing, and develop an approach that can generate multiple high-quality predictions given the same input. As a result, it can be used to generate high-quality outputs that are different from the observed ground truth.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=XCIKxMro5c