Logo Sam2Point

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

1CUHK MiuLar Lab, 2CUHK MMLab, 3ByteDance, 4Shanghai AI Laboratory

Introduction

We introduce Sam2Point, a preliminary exploration adapting Segment Anything Model 2 (SAM 2) for zero-shot and promptable 3D segmentation. 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 scenes, and raw LiDAR.

data-overview

The Segmentation Paradigm of Sam2Point.

To our best knowledge, Sam2Point presents the most faithful implementation of SAM in 3D, demonstrating superior implementation efficiency, promptable flexibility, and generalization capabilities for 3D segmentation..

data-overview

Comparison of Sam2Point and Previous SAM-based Methods.

Demonstrations of Sam2Point

We showcase demonstrations of Sam2Point in segmenting 3D data with various 3D prompt on different datasets.

Multi-directional Videos from Sam2Point

We showcase the multi-directional videos generated during the segmentation of Sam2Point.

Citation

@article{guo2024sam2point,
  	title={SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners},
  	author={Guo, Ziyu and Zhang, Renrui and Zhu, Xiangyang and Tong, Chengzhuo and Gao, Peng and Li, Chunyuan and Heng, Pheng-Ann},
  	journal={arXiv},
  	year={2024}
}