Multiscale structural similarity for image quality assessment
The structural similarity image quality paradigm is based on the assumption that the human visual system is highly adapted for extracting structural information from the scene, and therefore a measure of structural similarity can provide a good approximation to perceived image quality. This paper proposes a multiscale structural similarity method, which supplies more flexibility than previous single-scale methods in incorporating the variations of viewing conditions. We develop an image synthesis method to calibrate the parameters that define the relative importance of different scales. Experimental comparisons demonstrate the effectiveness of the proposed method.
PDF AbstractCode
Datasets
Results from the Paper
Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
---|---|---|---|---|---|---|
Video Quality Assessment | MSU FR VQA Database | MS-SSIM | SRCC | 0.9026 | # 8 | |
PLCC | 0.9375 | # 5 | ||||
KLCC | 0.7625 | # 6 | ||||
Video Quality Assessment | MSU SR-QA Dataset | MS-SSIM | SROCC | 0.11017 | # 59 | |
PLCC | 0.16035 | # 56 | ||||
KLCC | 0.07821 | # 60 | ||||
Type | FR | # 1 | ||||
Video Quality Assessment | MSU SR-QA Dataset | MS-SSIM Superfast | SROCC | 0.21604 | # 53 | |
PLCC | 0.30014 | # 48 | ||||
KLCC | 0.16578 | # 53 | ||||
Type | FR | # 1 | ||||
Video Quality Assessment | MSU SR-QA Dataset | MS-SSIM Precise | SROCC | 0.23108 | # 51 | |
PLCC | 0.20935 | # 52 | ||||
KLCC | 0.17468 | # 51 | ||||
Type | FR | # 1 | ||||
Video Quality Assessment | MSU SR-QA Dataset | MS-SSIM Fast | SROCC | 0.24422 | # 50 | |
PLCC | 0.21800 | # 51 | ||||
KLCC | 0.18174 | # 50 | ||||
Type | FR | # 1 |