Categorical Subjective Image Quality
The CSIQ database consists of 30 original images, each is distorted using six different types of distortions at four to five different levels of distortion. CSIQ images are subjectively rated base on a linear displacement of the images across four calibrated LCD monitors placed side by side with equal viewing distance to the observer. The database contains 5000 subjective ratings from 35 different observers, and ratings are reported in the form of DMOS.
Variants: CSIQ
This dataset is used in 1 benchmark:
| Task | Model | Paper | Date |
|---|---|---|---|
| No-Reference Image Quality Assessment | ARNIQA | ARNIQA: Learning Distortion Manifold for … | 2023-10-20 |
| No-Reference Image Quality Assessment | UNIQA | You Only Train Once: A … | 2023-10-14 |
| No-Reference Image Quality Assessment | Re-IQA | Re-IQA: Unsupervised Learning for Image … | 2023-04-02 |
| No-Reference Image Quality Assessment | CONTRIQUE | Image Quality Assessment using Contrastive … | 2021-10-25 |
| No-Reference Image Quality Assessment | TReS | No-Reference Image Quality Assessment via … | 2021-08-16 |
| No-Reference Image Quality Assessment | DB-CNN | Blind Image Quality Assessment Using … | 2019-07-05 |
Recent papers with results on this dataset: