Skip to Main content Skip to Navigation
Conference papers

DR2S : Deep Regression with Region Selection for Camera Quality Evaluation

Abstract : In this work, we tackle the problem of estimating a camera capability to preserve fine texture details at a given lighting condition. Importantly, our texture preservation measurement should coincide with human perception. Consequently, we formulate our problem as a regression one and we introduce a deep convolutional network to estimate texture quality score. At training time, we use ground-truth quality scores provided by expert human annotators in order to obtain a subjective quality measure. In addition, we propose a region selection method to identify the image regions that are better suited at measuring perceptual quality. Finally, our experimental evaluation shows that our learning-based approach outperforms existing methods and that our region selection algorithm consistently improves the quality estimation.
Document type :
Conference papers
Complete list of metadata

https://hal.telecom-paris.fr/hal-03108408
Contributor : Stéphane Lathuilière <>
Submitted on : Wednesday, January 13, 2021 - 10:42:30 AM
Last modification on : Tuesday, September 21, 2021 - 2:16:05 PM

Links full text

Identifiers

  • HAL Id : hal-03108408, version 1
  • ARXIV : 2009.09981

Collections

Citation

Marcelin Tworski, Stéphane Lathuilière, Salim Belkarfa, Attilio Fiandrotti, Marco Cagnazzo. DR2S : Deep Regression with Region Selection for Camera Quality Evaluation. International Conference on Pattern Recognition (ICPR 2020), Jan 2021, Milano, Italy. ⟨hal-03108408⟩

Share

Metrics

Record views

171