Deep Generative Model based Rate-Distortion for Image Downscaling Assessment

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liang, Yuanbang, Garg, Bhavesh, Rosin, Paul L, Qin, Yipeng
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914724813209600
author Liang, Yuanbang
Garg, Bhavesh
Rosin, Paul L
Qin, Yipeng
author_facet Liang, Yuanbang
Garg, Bhavesh
Rosin, Paul L
Qin, Yipeng
contents 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 distorted 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 recent SR algorithms based on deep generative models that can find all matching HR images for a given LR image on their learned image manifolds. Extensive experimental results show the effectiveness of our IDA-RD measure.
format Preprint
id arxiv_https___arxiv_org_abs_2403_15139
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep Generative Model based Rate-Distortion for Image Downscaling Assessment
Liang, Yuanbang
Garg, Bhavesh
Rosin, Paul L
Qin, Yipeng
Computer Vision and Pattern Recognition
Image and Video Processing
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 distorted 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 recent SR algorithms based on deep generative models that can find all matching HR images for a given LR image on their learned image manifolds. Extensive experimental results show the effectiveness of our IDA-RD measure.
title Deep Generative Model based Rate-Distortion for Image Downscaling Assessment
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2403.15139