Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network
Blind image quality assessment (BIQA) for authentically distorted images has always been a challenging problem, since images captured in the wild include varies contents and diverse types of distortions. The vast majority of prior BIQA methods focus on how to predict synthetic image quality, but fail when applied to real-world distorted images. To deal with the challenge, we propose a self-adaptive hyper network architecture to blind assess image quality in the wild. We separate the IQA procedure into three stages including content understanding, perception rule learning and quality predicting. After extracting image semantics, perception rule is established adaptively by a hyper network, and then adopted by a quality prediction network. In our model, image quality can be estimated in a self-adaptive manner, thus generalizes well on diverse images captured in the wild. Experimental results verify that our approach not only outperforms the state-of-the-art methods on challenging authentic image databases but also achieves competing performances on synthetic image databases, though it is not explicitly designed for the synthetic task.
PDF AbstractCode
ImageNet
KonIQ-10k
KADID-10k
TID2013
Results from the Paper
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| No-Reference Image Quality Assessment | CSIQ | HyperIQA | SRCC | 0.923 | # 6 | |
| PLCC | 0.942 | # 6 | ||||
| No-Reference Image Quality Assessment | KADID-10k | HyperIQA | SRCC | 0.852 | # 6 | |
| PLCC | 0.845 | # 7 | ||||
| Video Quality Assessment | MSU SR-QA Dataset | HyperIQA | SROCC | 0.59883 | # 20 | |
| PLCC | 0.55211 | # 26 | ||||
| KLCC | 0.48466 | # 19 | ||||
| Type | NR | # 1 | ||||
| No-Reference Image Quality Assessment | TID2013 | HyperIQA | SRCC | 0.840 | # 5 | |
| PLCC | 0.858 | # 6 |
