No Reference Image Quality Assessment On Csiq
评估指标
PLCC
SRCC
评测结果
各个模型在此基准测试上的表现结果
| Paper Title | Repository | |||
|---|---|---|---|---|
| ARNIQA | 0.973 | 0.962 | ARNIQA: Learning Distortion Manifold for Image Quality Assessment | |
| UNIQA | 0.970 | 0.964 | You Only Train Once: A Unified Framework for Both Full-Reference and No-Reference Image Quality Assessment | |
| Re-IQA | 0.960 | 0.947 | Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild | |
| DB-CNN | 0.959 | 0.946 | Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network | |
| CONTRIQUE | 0.955 | 0.942 | Image Quality Assessment using Contrastive Learning | |
| TReS | 0.942 | 0.922 | No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency | |
| HyperIQA | 0.942 | 0.923 | Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network | - |
| BRISQUE | 0.829 | 0.746 | No-Reference Image Quality Assessment in the Spatial Domain | - |
0 of 8 row(s) selected.