Sorry, you need to enable JavaScript to visit this website.

Self-Supervised Face Image Restoration with a One-Shot Reference

DOI:
10.60864/xd5k-9x62
Citation Author(s):
Submitted by:
Yanhui Guo
Last updated:
6 June 2024 - 10:50am
Document Type:
Presentation Slides
Document Year:
2024
Event:
Paper Code:
IVMSP-L4.3
 

For image restoration, methods leveraging priors from generative models have been proposed and demonstrated a promising capacity to robustly restore photorealistic and high-quality results. However, these methods are susceptible to semantic ambiguity, particularly with images that have obviously correct semantics, such as facial images. In this paper, we propose a semantic-aware latent space exploration method for image restoration (SAIR). By explicitly modelling semantic information from a given reference image, SAIR is able to reliably restore severely degraded images not only to high-resolution and highly realistic looks but also to correct semantics. Quantitative and qualitative experiments collectively demonstrate the superior performance of the proposed SAIR. Our code is available at https://github.com/Liamkuo/SAIR.

up
0 users have voted: