Deep generative model based rate-distortion for image downscaling assessment

Liang, Yuanbang ORCID: https://orcid.org/0009-0000-8370-6655, Garg, Bhavesh, Rosin, Paul ORCID: https://orcid.org/0000-0002-4965-3884 and Qin, Yipeng ORCID: https://orcid.org/0000-0002-1551-9126 2024. Deep generative model based rate-distortion for image downscaling assessment. Presented at: The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2024, Seattle, WA, USA, 17-21 June 2024. Proceedings of the Conference on Computer Vision and Pattern Recognition. IEEE, pp. 19363-19372. 10.1109/CVPR52733.2024.01832

Preview

PDF - Presentation Download (24MB) | Preview

Abstract

In this paper, we propose Image Downscaling Assessment by Rate-Distortion (IDA-RD), a novel measure to quantitatively evaluate image downscaling algorithms. In contrast to image-based methods that measure the quality of downscaled images, ours is process-based that draws ideas from rate-distortion theory to measure the distortion incurred during downscaling. Our main idea is that downscaling and super-resolution (SR) can be viewed as the encoding and decoding processes in the rate-distortion model, respectively, and that a downscaling algorithm that preserves more details in the resulting low-resolution (LR) images should lead to less dis-torted high-resolution (HR) images in SR. In other words, the distortion should increase as the downscaling algorithm deteriorates. However, it is non-trivial to measure this distortion as it requires the SR algorithm to be blind and stochastic. Our key insight is that such requirements can be met by re-cent SR algorithms based on deep generative models that can find all matching HR images for a given LR image on their learned manifolds. Extensive experimental results show the effectiveness of our IDA-RD measure. Our code is available at: https://github.com/Byronliang8/Ida-Rd

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Professional Services > Advanced Research Computing @ Cardiff (ARCCA) Schools > Computer Science & Informatics
Publisher:	IEEE
ISBN:	979-8-3503-5301-3
ISSN:	1063-6919
Date of Acceptance:	27 February 2024
Last Modified:	02 Apr 2025 12:09
URI:	https://orca.cardiff.ac.uk/id/eprint/167382

Actions (repository staff only)

Edit Item