🏢 State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA
SEAGULL: No-reference Image Quality Assessment for Regions of Interest via Vision-Language Instruction Tuning
·2623 words·13 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Computer Vision
Image Quality Assessment
🏢 State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA
SEAGULL: A novel network uses vision-language instruction tuning to assess image quality for regions of interest (ROIs) with high accuracy, leveraging masks and a new dataset for fine-grained IQA.