CAV-SAM reformulates reference segmentation as pseudo-video object segmentation using diffusion-based semantic transitions and test-time geometric alignment, claiming over 5% improvement over state-of-the-art.
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
-
Correspondence as Video: Test-Time Adaption on SAM2 for Reference Segmentation in the Wild
CAV-SAM reformulates reference segmentation as pseudo-video object segmentation using diffusion-based semantic transitions and test-time geometric alignment, claiming over 5% improvement over state-of-the-art.