Defying Limits: Super-Resolution Refinement with Diffusion Guidance

Marcelo Santos, João C. R. Neves, Hugo Proença, David Menotti

2024

Abstract

Due to the growing number of surveillance cameras and rapid technological advancement, facial recognition algorithms have been widely applied. However, their performance decreases in challenging environments, such as those involving surveillance cameras with low-resolution images. To address this problem, in this paper, we introduce SRDG, a super-resolution approach supported by two state-of-the-art methods: diffusion models and classifier guidance. The diffusion process reconstructs the image, and the classifier refines the image reconstruction based on a set of facial attributes. This combination of models is capable of working with images with a very limited resolution (8×8 and 16×16), being suitable for surveillance scenarios where subjects are typically distant from the camera. The experimental validation of the proposed approach shows that super-resolution images exhibit enhanced details and improved visual quality. More importantly, when using our super-resolution algorithm, the facial discriminability of images is improved compared to state-of-the-art super-resolution approaches, resulting in a significant increase in face recognition accuracy. To the best of our knowledge, this is the first time classifier guidance has been applied to refine super-resolution results of images from surveillance cameras. Source code is available at https://github.com/marcelowds/SRDG.

Paper Citation

in Harvard Style

Santos M., C. R. Neves J., Proença H. and Menotti D. (2024). Defying Limits: Super-Resolution Refinement with Diffusion Guidance. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 426-434. DOI: 10.5220/0012398900003660

in Bibtex Style

@conference{visapp24,
author={Marcelo Santos and João C. R. Neves and Hugo Proença and David Menotti},
title={Defying Limits: Super-Resolution Refinement with Diffusion Guidance},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP},
year={2024},
pages={426-434},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012398900003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP
TI - Defying Limits: Super-Resolution Refinement with Diffusion Guidance
SN - 978-989-758-679-8
AU - Santos M.
AU - C. R. Neves J.
AU - Proença H.
AU - Menotti D.
PY - 2024
SP - 426
EP - 434
DO - 10.5220/0012398900003660
PB - SciTePress