AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learning

Kwan-Yee Lin, Guanxiang Wang

CVPR 2018 · Image generation › Autoregressive and latent generation · approach: Learning-based image quality assessment · 257 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
Pair distorted images with generated hallucinated references and their discrepancy maps (ablation)NR-IQA regression on TID2008 · TID2008SROCC: 0.755 -> 0.859Improved
Add hallucinated-reference compensation (ablation)NR-IQA regression on TID2008 · TID2008LCC: 0.800 -> 0.870Improved
Add quality-aware perceptual loss to the hallucination model (ablation)BL+HCM on TID2008 · TID2008SROCC: 0.859 -> 0.864Improved
Add quality-aware perceptual loss to the hallucination model (ablation)BL+HCM on TID2008 · TID2008LCC: 0.870 -> 0.887Improved
Add the original adversarial-learning mechanism (ablation)BL+HCM+QPL on TID2008 · TID2008SROCC: 0.864 -> 0.894Improved
Add the original adversarial-learning mechanism (ablation)BL+HCM+QPL on TID2008 · TID2008LCC: 0.887 -> 0.910Improved
Replace original adversarial learning with the proposed quality-aware adversarial mechanism (ablation)BL+HCM+QPL+ADV on TID2008 · TID2008SROCC: 0.894 -> 0.910Improved
Replace original adversarial learning with the proposed quality-aware adversarial mechanism (ablation)BL+HCM+QPL+ADV on TID2008 · TID2008LCC: 0.910 -> 0.918Improved
Add high-level semantic fusion between generator and regression features (ablation)BL+HCM+QPL+QADV on TID2008 · TID2008SROCC: 0.910 -> 0.941Improved
Add high-level semantic fusion between generator and regression features (ablation)BL+HCM+QPL+QADV on TID2008 · TID2008LCC: 0.918 -> 0.949Improved
Train the hallucination generator using TID2008 and TID2013 rather than LIVE alone (ablation)Hallucinated-IQA trained on LIVE · LIVESROCC: 0.982 -> 0.982No clear effect

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