Quality Assessment for Tone-Mapped HDR Images Using Multi-Scale and Multi-Layer Information
This addresses the need for quality evaluation in image processing for HDR content, but it is incremental as it builds on existing no-reference methods with specific feature improvements.
The paper tackles the problem of assessing the quality of tone-mapped HDR images, which often have distortions, by proposing a no-reference method using multi-scale and multi-layer features from a pre-trained CNN, achieving better performance on the largest public database compared to existing methods.
Tone mapping operators and multi-exposure fusion methods allow us to enjoy the informative contents of high dynamic range (HDR) images with standard dynamic range devices, but also introduce distortions into HDR contents. Therefore methods are needed to evaluate tone-mapped image quality. Due to the complexity of possible distortions in a tone-mapped image, information from different scales and different levels should be considered when predicting tone-mapped image quality. So we propose a new no-reference method of tone-mapped image quality assessment based on multi-scale and multi-layer features that are extracted from a pre-trained deep convolutional neural network model. After being aggregated, the extracted features are mapped to quality predictions by regression. The proposed method is tested on the largest public database for TMIQA and compared to existing no-reference methods. The experimental results show that the proposed method achieves better performance.