Bridging the Synthetic-to-Authentic Gap: Distortion-Guided Unsupervised Domain Adaptation for Blind Image Quality Assessment

arXiv:2405.04167v1 Announce Type: new
Abstract: 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 beneficial, but synthetically trained models often suffer from poor generalization in real domains due to domain gaps. In this work, we make a key observation that introducing more distortion types in the synthetic dataset may not improve or even be harmful to generalizing authentic image quality assessment. To solve this challenge, …

abstract annotation arxiv assessment authentic blind cs.cv data domain domain adaptation domains eess.iv gap image images labor quality synthetic synthetic data training type unsupervised