AI Dynamics

Global AI News Aggregator

About

SAM2Point: Zero-shot 3D Segmentation Using Segment Anything Model 2

SAM2Point Segment Any 3D as Videos in Zero-shot and Promptable Manners discuss: https://
huggingface.co/papers/2408.16
768
… We introduce SAM2Point, a preliminary exploration adapting Segment Anything Model 2 (SAM 2) for zero-shot and promptable 3D segmentation. SAM2Point interprets any 3D data as

→ View original post on X — @_akhaliq