SC-AGIQA combines MLLM-generated image descriptions with HVS-inspired frequency-domain pooling to set new state-of-the-art scores on three AGIQA benchmarks.
Blind image quality assessment using a deep bilinear convolutional neural network,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Text-Visual Semantic Constrained AI-Generated Image Quality Assessment
SC-AGIQA combines MLLM-generated image descriptions with HVS-inspired frequency-domain pooling to set new state-of-the-art scores on three AGIQA benchmarks.