No-Reference Image Quality Assessment on LIVEW 1.0 (test)
0.893PLCCQ-Insight†
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Q-Insight†Method Category=VLM-based, Training Protocol=Multi-task training set in [25] for GRPO calibration2026.03 | 0.893 | 0.865 | |
| DeQA-ScoreMethod Category=VLM-based, Training Protocol=Trained on KonIQ-10K2026.03 | 0.892 | 0.879 | |
| Q-Tacit†Method Category=VLM-based, Training Protocol=Multi-task training set in [25] for GRPO calibration2026.03 | 0.89 | 0.866 | |
| Q-TacitMethod Category=VLM-based, Training Protocol=Trained on KonIQ-10K2026.03 | 0.875 | 0.832 | |
| VisualQuality-R1Method Category=VLM-based, Training Protocol=Trained on KonIQ-10K2026.03 | 0.873 | 0.841 | |
| Q-InsightMethod Category=VLM-based, Training Protocol=Trained on KonIQ-10K2026.03 | 0.87 | 0.839 | |
| Q-AlignMethod Category=VLM-based, Training Protocol=Trained on KonIQ-10K2026.03 | 0.853 | 0.86 | |
| ManIQAMethod Category=Non-VLM Deep-learning, Training Protocol=Trained on KonIQ-10K2026.03 | 0.849 | 0.832 | |
| CLIP-IQA+Method Category=Non-VLM Deep-learning, Training Protocol=Trained on KonIQ-10K2026.03 | 0.832 | 0.805 | |
| NIMAMethod Category=Non-VLM Deep-learning, Training Protocol=Trained on KonIQ-10K2026.03 | 0.814 | 0.771 | |
| MUSIQMethod Category=Non-VLM Deep-learning, Training Protocol=Trained on KonIQ-10K2026.03 | 0.789 | 0.83 | |
| Compare2ScoreMethod Category=VLM-based, Training Protocol=Trained on KonIQ-10K2026.03 | 0.786 | 0.772 | |
| Qwen-2.5-VL-7BMethod Category=VLM-based, Training Protocol=Trained on KonIQ-10K2026.03 | 0.734 | 0.728 | |
| NIQEMethod Category=Handcrafted, Training Protocol=Trained on KonIQ-10K2026.03 | 0.493 | 0.449 | |
| BRISQUEMethod Category=Handcrafted, Training Protocol=Trained on KonIQ-10K2026.03 | 0.361 | 0.313 |