3 papers
cs.CV2026
Towards Syn-to-Real IQA: A Novel Perspective on Reshaping Synthetic Data Distributions
Aobo Li, Jinjian Wu, Yongxu Liu +2
Blind Image Quality Assessment (BIQA) has advanced significantly through deep learning, but the scarcity of large-scale labeled datasets remains a challenge. While synthetic data o…
cs.CV2024
Bridging the Synthetic-to-Authentic Gap: Distortion-Guided Unsupervised Domain Adaptation for Blind Image Quality Assessment
Aobo Li, Jinjian Wu, Yongxu Liu +1
The annotation of blind image quality assessment (BIQA) is labor-intensive and time-consuming, especially for authentic images. Training on synthetic data is expected to be benefic…
cs.CV2024
Scaling and Masking: A New Paradigm of Data Sampling for Image and Video Quality Assessment
Yongxu Liu, Yinghui Quan, Guoyao Xiao +2
Quality assessment of images and videos emphasizes both local details and global semantics, whereas general data sampling methods (e.g., resizing, cropping or grid-based fragment)…