BestHub
Sign in
AIWalker
AIWalker
Aug 3, 2025 · Artificial Intelligence

CVPR 2025: DeQA-Score Lets LLMs Predict Image Quality Score Distributions

DeQA-Score introduces a soft‑label discretization that lets multimodal large language models regress continuous image‑quality scores as Gaussian distributions, achieving 30× lower mean error and preserving variance and inter‑image relationships, with KL‑divergence and fidelity losses driving state‑of‑the‑art performance.

CVPR2025DeQA-Scoreimage quality assessment
0 likes · 8 min read
CVPR 2025: DeQA-Score Lets LLMs Predict Image Quality Score Distributions
AIWalker
AIWalker
Apr 11, 2025 · Artificial Intelligence

Teaching Large Language Models to Predict Image Quality Scores with DeQA-Score

DeQA-Score, a CVPR 2025 work, shows how to train multimodal large language models to regress continuous image quality scores by discretizing scores into soft-label level tokens, preserving Gaussian distribution statistics and achieving state‑of‑the‑art performance without any installation.

CVPR2025DeQA-Scoreimage quality assessment
0 likes · 8 min read
Teaching Large Language Models to Predict Image Quality Scores with DeQA-Score