No-reference Image Quality Assessment on PIPAL
0.649PLCCEvoQuality
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| EvoQualityModel Category=VLM-based, Zero-shot evaluation=true, Evolution Round=Round 22025.09 | 0.649 | 0.583 | |
| ME-IQABase VLM=EvoQuality2026.03 | 0.642 | 0.588 | |
| ME-IQABase VLM=Q-Insight2026.03 | 0.635 | 0.566 | |
| EvoQualityModel Category=VLM-based, Zero-shot evaluation=true, Evolution Round=Round 12025.09 | 0.613 | 0.545 | |
| DeQA-ScoreModel Type=Non-reasoning2026.03 | 0.608 | 0.565 | |
| DeQA-ScoreModel Category=VLM-based, Zero-shot evaluation=true2025.09 | 0.608 | 0.565 | |
| Q-InsightModel Category=VLM-based, Zero-shot evaluation=true2025.09 | 0.608 | 0.534 | |
| BaselineBase VLM=Q-Insight2026.03 | 0.604 | 0.528 | |
| MANIQAModel Type=Non-reasoning2026.03 | 0.603 | 0.551 | |
| MANIQAModel Category=Discriminative Deep-Learning-based, Zero-shot evaluation=true2025.09 | 0.603 | 0.551 | |
| BaselineBase VLM=EvoQuality2026.03 | 0.602 | 0.543 | |
| Q-AlignModel Type=Non-reasoning2026.03 | 0.6 | 0.518 | |
| Q-AlignModel Category=VLM-based, Zero-shot evaluation=true2025.09 | 0.6 | 0.518 | |
| ME-IQABase VLM=VisualQuality-R12026.03 | 0.599 | 0.551 | |
| Compare2ScoreModel Type=Non-reasoning2026.03 | 0.596 | 0.588 | |
| MUSIQModel Type=Non-reasoning2026.03 | 0.567 | 0.535 | |
| BaselineBase VLM=VisualQuality-R12026.03 | 0.567 | 0.509 | |
| MUSIQModel Category=Discriminative Deep-Learning-based, Zero-shot evaluation=true2025.09 | 0.567 | 0.535 | |
| ME-IQABase VLM=GPT-52026.03 | 0.566 | 0.56 | |
| ME-IQABase VLM=Doubao-Seed-1.6-vision2026.03 | 0.561 | 0.533 | |
| CLIP-IQA+Model Type=Non-reasoning2026.03 | 0.55 | 0.499 | |
| CLIP-IQA+Model Category=Discriminative Deep-Learning-based, Zero-shot evaluation=true2025.09 | 0.55 | 0.499 | |
| BaselineBase VLM=GPT-52026.03 | 0.539 | 0.496 | |
| NIMAModel Type=Non-reasoning2026.03 | 0.536 | 0.486 | |
| NIMAModel Category=Discriminative Deep-Learning-based, Zero-shot evaluation=true2025.09 | 0.536 | 0.486 | |
| VisualQuality-R1Model Category=VLM-based, Zero-shot evaluation=true2025.09 | 0.531 | 0.486 | |
| BaselineBase VLM=Doubao-Seed-1.6-vision2026.03 | 0.517 | 0.483 | |
| HyperIQAModel Category=Discriminative Deep-Learning-based, Zero-shot evaluation=true2025.09 | 0.511 | 0.461 | |
| DBCNNModel Category=Discriminative Deep-Learning-based, Zero-shot evaluation=true2025.09 | 0.469 | 0.408 | |
| Qwen2.5-VL-7BModel Category=VLM-based, Zero-shot evaluation=true2025.09 | 0.444 | 0.388 | |
| CONTRIQUEModel Category=Discriminative Deep-Learning-based, Zero-shot evaluation=true2025.09 | 0.416 | 0.341 | |
| BRISQUEModel Category=Handcrafted, Zero-shot evaluation=true2025.09 | 0.412 | 0.279 | |
| NIQEModel Category=Handcrafted, Zero-shot evaluation=true2025.09 | 0.372 | 0.12 | |
| Re-IQAModel Category=Discriminative Deep-Learning-based, Zero-shot evaluation=true2025.09 | 0.354 | 0.281 | |
| NIQEModel Type=Non-reasoning2026.03 | 0.12 | 0.12 |