AI RESEARCH
Comparing SAM 2 and SAM 3 for Zero-Shot Segmentation of 3D Medical Data
arXiv CS.CV
•
ArXi:2511.21926v2 Announce Type: replace-cross Foundation models, such as the Segment Anything Model (SAM), have heightened interest in promptable zero-shot segmentation. Although these models perform strongly on natural images, their behavior on medical data remains insufficiently characterized. While SAM 2 has been widely adopted for annotation in 3D medical workflows, the recently released SAM 3