3260 papers • 126 benchmarks • 313 datasets
This task has no description! Would you like to contribute one?
(Image credit: Papersgraph)
These leaderboards are used to track progress in stereoscopic-image-quality-assessment-7
No benchmarks available.
Use these libraries to find stereoscopic-image-quality-assessment-7 models and implementations
No datasets available.
No subtasks available.
Experimental results have demonstrated that the proposed metric performance achieves high consistency with subjective assessment and outperforms the blind stereo IQA over various types of distortion.
This paper addresses the problem of blind stereoscopic image quality assessment (NR-SIQA) using a new multi-task deep learning based-method and compute naturalness-based features using a Natural Scene Statistics (NSS) model in the complex wavelet domain.
A blind stereoscopic image quality measurement using synthesized cyclopean image and deep feature extraction based on Human Visual System (HVS) modeling and quality-aware indicators is introduced.
A new deep learning-based no-reference SIQA using cyclopean view hypothesis and human visual attention is introduced using cyclopean view hypothesis and human visual attention.
A deep multi-score Convolutional Neural Network that has been trained to perform four tasks: predict the left view’s quality, predict the quality of the stereo view and global quality, respectively, with the global score serving as the ultimate quality.
Adding a benchmark result helps the community track progress.