RSFIQA uses SAM-based image segmentation and MLLM-generated region descriptions with a region-aware attention mechanism to predict no-reference image quality.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Segmenting and Understanding: Region-aware Semantic Attention for Fine-grained Image Quality Assessment with Large Language Models
RSFIQA uses SAM-based image segmentation and MLLM-generated region descriptions with a region-aware attention mechanism to predict no-reference image quality.