TIP 2026
sym

Zewen Chen, Juan Wang, Wen Wang, Sunhan Xu, et al.

IEEE Transactions on Image Processing (TIP), 2026

TL;DR: We propose a novel network (SEAGULL) and construct two datasets (SEAGULL-1M and SEAGULL-3K) to achieve fine-grained IQA for any ROIs.

Paper Open in Spaces
Quick Read (Click Me) Existing Image Quality Assessment (IQA) methods achieve remarkable success in analyzing quality for overall image, but few works explore quality analysis for Regions of Interest (ROIs). The quality analysis of ROIs can provide fine-grained guidance for image quality improvement and is crucial for scenarios focusing on region-level quality. This paper proposes a novel network, SEAGULL, which can SEe and Assess ROIs quality with GUidance from a Large vision-Language model. SEAGULL incorporates a vision-language model (VLM), masks generated by Segment Anything Model (SAM) to specify ROIs, and a meticulously designed Mask-based Feature Extractor (MFE) to extract global and local tokens for specified ROIs, enabling accurate fine-grained IQA for ROIs. Moreover, this paper constructs two ROI-based IQA datasets, SEAGULL-1M and SEAGULL-3K, for training and evaluating ROI-based IQA. SEAGULL-1M comprises 1 million synthetically distorted images with 33 million ROIs for pre-training to improve the model's ability of regional quality perception, and SEAGULL-3K contains 3,261 authentically distorted ROIs to enhance the model's ability to perceive real-world distortions. After pre-training on SEAGULL-1M and fine-tuning on SEAGULL-3K, SEAGULL shows remarkable performance on fine-grained ROI quality assessment.