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

Ziyu Guo, Renrui Zhang, Zhu Xiangyang, Chengzhuo Tong, Peng Gao, Chunyuan Li, Pheng-Ann Heng

SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners: 28 upvotes on Hugging Face Daily Papers, #5 of 11 papers on 2024-08-30. Day-by-day upvote history.

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 .

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.