Affordable Access

Access to the full text

Comparison of Image Quality Models for Optimization of Image Processing Systems

Authors
  • Ding, Keyan
  • Ma, Kede
  • Wang, Shiqi
  • Simoncelli, Eero P.
Type
Published Article
Publication Date
Dec 08, 2020
Submission Date
May 04, 2020
Identifiers
DOI: 10.1007/s11263-020-01419-7
Source
arXiv
License
Yellow
External links

Abstract

The performance of objective image quality assessment (IQA) models has been evaluated primarily by comparing model predictions to human quality judgments. Perceptual datasets gathered for this purpose have provided useful benchmarks for improving IQA methods, but their heavy use creates a risk of overfitting. Here, we perform a large-scale comparison of IQA models in terms of their use as objectives for the optimization of image processing algorithms. Specifically, we use eleven full-reference IQA models to train deep neural networks for four low-level vision tasks: denoising, deblurring, super-resolution, and compression. Subjective testing on the optimized images allows us to rank the competing models in terms of their perceptual performance, elucidate their relative advantages and disadvantages in these tasks, and propose a set of desirable properties for incorporation into future IQA models.

Report this publication

Statistics

Seen <100 times