Papers
1–5 of 5EvoIQA - Explaining Image Distortions with Evolved White-Box Logic
Traditional Image Quality Assessment (IQA) metrics typically fall into one of two extremes: rigid, hand-crafted mathematical models or "black-box" deep learning architectures that completely lack inte...
Reference-Free Image Quality Assessment for Virtual Try-On via Human Feedback
Given a person image and a garment image, image-based Virtual Try-ON (VTON) synthesizes a try-on image of the person wearing the target garment. As VTON systems become increasingly important in practi...
TIQA: Human-Aligned Text Quality Assessment in Generated Images
Text rendering remains a persistent failure mode of modern text-to-image models (T2I), yet existing evaluations rely on OCR correctness or VLM-based judging procedures that are poorly aligned with per...
Self-Supervised Image Super-Resolution Quality Assessment based on Content-Free Multi-Model Oriented Representation Learning
Super-resolution (SR) applied to real-world low-resolution (LR) images often results in complex, irregular degradations that stem from the inherent complexity of natural scene acquisition. In contrast...
From Global to Granular: Revealing IQA Model Performance via Correlation Surface
Evaluation of Image Quality Assessment (IQA) models has long been dominated by global correlation metrics, such as Pearson Linear Correlation Coefficient (PLCC) and Spearman Rank-Order Correlation Coe...