In this work, we propose SAM3D, a novel framework that is able to predict masks in 3D point clouds by leveraging the Segment-Anything Model (SAM) in RGB images without further training or finetuning. For a point cloud of a 3D scene with posed RGB images, we first predict segmentation ma...
Given the 3D point cloud and multiple posed 2D frames of 3D scenes, our approach segments 3D scenes by applying the pretrained Segment Anything Model (SAM) to 2D frames. Our key idea involves locating 3D points in scenes as natural 3D prompts to align their projected pixel prompts across ...
[2] proposed a new vision foundation model for image segmentation, the segment anything model (SAM), trained on a huge dataset called SA-1B. The flexible prompting support, ambiguity awareness, and vast training data endow the SAM with powerful generalization, enabling the ability to solve ...
TinySAM: Pushing the Envelope for Efficient Segment Anything Model https://arxiv.org/abs/2312.13789 Han Shu, Wenshuo Li, Yehui Tang, Yiman Zhang, Yihao Chen, Houqiang Li, Yunhe Wang, Xinghao Chen 中科大、华为诺亚方舟实验室 近年来,分段任何模型(SAM)表现出了强大的分割能力,并引起了计算机视觉领...
We introduce SAM3D, a new approach to semi-automatic zero-shot segmentation of 3D images building on the existing Segment Anything Model. We achieve fast and accurate segmentations in 3D images with a four-step strategy involving: user prompting with 3D polylines, volume slicing along multiple ...
SAM3D: Zero-Shot Semi-Automatic Segmentation in 3D Medical Images with the Segment Anything Model We introduce SAM3D, a new approach to semi-automatic zero-shot segmentation of 3D images building on the existing Segment Anything Model. We achieve fast a... TJ Chan,A Sahni,Y Fang,... 被...
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...