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

Hypernetwork-based Adaptive Image Restoration

Citation Author(s):
Gil Ben-Artzi
Submitted by:
Shai Aharon
Last updated:
19 May 2023 - 12:23am
Document Type:
Poster
Document Year:
2022
Event:
Presenters:
Shai Aharon, Gil Ben-Artzi
Paper Code:
IVMSP-P13.1
 

Adaptive image restoration models can restore images with different degradation levels at inference time without the need to retrain the model. We present an approach that is highly accurate and allows a significant reduction in the number of parameters. In contrast to existing methods, our approach can restore images using a single fixed-size model, regardless of the number of degradation levels. On popular datasets, our approach yields state-of-the-art results in terms of size and accuracy for a variety of image restoration tasks, including denoising, deJPEG, and super-resolution.

up
3 users have voted: Shai Aharon, Yael Elkin, Amihay Elboher

Comments

Hi. This paper presents a cool work which does exactly what we all love: improve performance while reduce memory consumption. The ideas are clearly explained, the results are great, and the paper was also accepted lastly, so congratulations! Worth reading (: