SurgVisAgent combines a ResNet distortion-prior with GPT-4o chain-of-thought reasoning to classify distortion type and severity and invoke the appropriate enhancement model, outperforming single-task models on a synthetic surgical benchmark.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
SurgVisAgent: Multimodal Agentic Model for Versatile Surgical Visual Enhancement
SurgVisAgent combines a ResNet distortion-prior with GPT-4o chain-of-thought reasoning to classify distortion type and severity and invoke the appropriate enhancement model, outperforming single-task models on a synthetic surgical benchmark.