Back to Search Start Over

SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners

Authors :
Guo, Ziyu
Zhang, Renrui
Zhu, Xiangyang
Tong, Chengzhuo
Gao, Peng
Li, Chunyuan
Heng, Pheng-Ann
Publication Year :
2024

Abstract

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 a series of multi-directional videos, and leverages SAM 2 for 3D-space segmentation, without further training or 2D-3D projection. Our framework supports various prompt types, including 3D points, boxes, and masks, and can generalize across diverse scenarios, such as 3D objects, indoor scenes, outdoor environments, and raw sparse LiDAR. Demonstrations on multiple 3D datasets, e.g., Objaverse, S3DIS, ScanNet, Semantic3D, and KITTI, highlight the robust generalization capabilities of SAM2Point. To our best knowledge, we present the most faithful implementation of SAM in 3D, which may serve as a starting point for future research in promptable 3D segmentation. Online Demo: https://huggingface.co/spaces/ZiyuG/SAM2Point . Code: https://github.com/ZiyuGuo99/SAM2Point .<br />Comment: Work in progress. Online Demo: https://huggingface.co/spaces/ZiyuG/SAM2Point . Code: https://github.com/ZiyuGuo99/SAM2Point

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2408.16768
Document Type :
Working Paper