AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts

Zewen Chen, Haina Qin, Juan Wang, Chunfeng Yuan, Bing Li, Weiming Hu, Leon Wang

ECCV 2024 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 23 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Remove the image-score prompt components (w/o prompt) (ablation)PromptIQA · Generalization TID2013 FSIM(MOS)PLCC: 0.7851 -> 0.8802Improved
Add image-score prompt (ISPP) to mixed training (ablation)PromptIQA · Generalization Kadid-10k LPIPS(DMOS)PLCC: -0.7397 -> 0.7615Improved
Add random scaling and random flipping augmentations (ablation)PromptIQA · Generalization Kadid-10k LPIPS(DMOS)PLCC: 0.4960 -> 0.7615Improved
Add random scaling and flipping augmentations (ablation)PromptIQA · Mixed test set TID2013PLCC: 0.9028 -> 0.9223Improved
Add random scaling and flipping augmentations (ablation)PromptIQA · Mixed test set UWIQAPLCC: 0.8791 -> 0.8839No clear effect
Train on the mixed 12 datasets instead of a single dataset (ablation)PromptIQA · Generalization TID2013 LPIPS(DMOS)PLCC: 0.6511 -> 0.8064Improved
Use interval sampling instead of random sampling for ISPs (ablation)PromptIQA · Kadid-10kSROCC: 0.9179 -> 0.9277Improved
Use random ISP selection on UWIQA (ablation)PromptIQA · UWIQASROCC: 0.8766 -> 0.8773No clear effect
Replace images or scores in the prompt with random numbers (ablation)PromptIQA · TID2013SROCC: 0.9030 -> 0.1287Hurt
Compared with the task-specific MoNet, use mixed-training PromptIQA on synthetic-distortion datasetsPromptIQA · SDN-IQA averageSROCC: 0.9263 -> 0.9231Hurt
Use 10 prompt images with no fine-tuning instead of fine-tuning baselines on the same 10 ISPsPromptIQA vs MANIQA and MoNet · TID2013 with FSIM(MOS) labelsPLCC: 0.8422 -> 0.8802Improved
Increase number of ISPs in the prompt (3 to 10) (ablation)PromptIQA · LIVEC, BID, SPAQperformanceImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy