REVEAL, a flow-matching generative model pretrained on 4.8 million endoscopic frames with domain-adapted representation alignment, produces high-fidelity endoscopy images and features that beat EndoViT and Endo-FM on classification benchmarks.
IEEE Access12, 25668–25683 (2024)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Representation-driven Endoscopic Visual Embedding Alignment for Latent Generation
REVEAL, a flow-matching generative model pretrained on 4.8 million endoscopic frames with domain-adapted representation alignment, produces high-fidelity endoscopy images and features that beat EndoViT and Endo-FM on classification benchmarks.