SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning

doi:arXiv:2411.10161

	SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning
	Chen, Zewen 1,2; Wang, Juan 1; Wang, Wen 3; Xu, Sunhan 4; Xiong, Hang 3; Zeng, Yun 5; Guo, Jian 4; Wang, Shuxun 1; Yuan, Chunfeng 1; Li, Bing 1,6; Hu, Weiming1,2,7
	2024-11-15
状态	已发表
摘要	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-100w and SEAGULL-3k, for training and evaluating ROI-based IQA. SEAGULL-100w comprises about 100w synthetic distortion images with 33 million ROIs for pre-training to improve the model's ability of regional quality perception, and SEAGULL-3k contains about 3k authentic distortion ROIs to enhance the model's ability to perceive real world distortions. After pre-training on SEAGULL-100w and fine-tuning on SEAGULL-3k, SEAGULL shows remarkable performance on fine-grained ROI quality assessment.Â
语种	英语
DOI	arXiv:2411.10161
相关网址	查看原文
出处	Arxiv
收录类别	PPRN.PPRN
WOS记录号	PPRN:119244441
WOS类目	Computer Science, Software Engineering
文献类型	预印本
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/464724
专题	信息科学与技术学院
通讯作者	Li, Bing
作者单位	1.CASIA, State Key Lab Multimodal Artificial Intelligence Syst, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 3.Beijing Jiaotong Univ, Beijing, Peoples R China 4.Beijing Union Univ, Beijing, Peoples R China 5.China Univ Petr, Beijing, Peoples R China 6.PeopleAI Inc, Beijing, Peoples R China 7.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Chen, Zewen,Wang, Juan,Wang, Wen,et al. SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning. 2024.