Exploring Open Domain Image Super-Resolution through Text

Published in ICML 2023 Workshop on Artificial Intelligence & Human-Computer Interaction, 2023

Kanchana Vaishnavi Gandikota, Paramanand Chandramouli

Teaser Image

Abstract

In this work, we propose for the first time a zero-shot approach for flexible open domain extreme super-resolution of images which allows users to interactively explore plausible solutions by using language prompts. Our approach exploits a recent diffusion based text-to-image (T2I) generative model. We modify the generative process of the T2I diffusion model to analytically enforce data consistency of the solution and explore diverse contents of null-space using text guidance. Our approach results in diverse solutions which are simultaneously consistent with input text and the low resolution images.

Resources

[pdf]

Bibtex

@misc{ gandikota2023exploring, title={Exploring Open Domain Image Super-Resolution through Text}, author={Kanchana Vaishnavi Gandikota and Paramanand Chandramouli}, booktitle={ICML 2023 Workshop on Artificial Intelligence & Human-Computer Interaction}, year={2023} }