DR2S : Deep Regression with Region Selection for Camera Quality Evaluation

TL;DR

This paper introduces DR2S, a deep learning regression model with region selection that estimates camera texture quality in a way that aligns with human perception, outperforming existing methods.

Contribution

The paper presents a novel deep regression framework with a region selection technique for camera quality evaluation based on human perceptual scores.

Findings

Outperforms existing camera quality assessment methods.

Region selection improves estimation accuracy.

Deep regression effectively models subjective texture quality.

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.