相关实验视频

Updated: Jul 6, 2026

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

端到端的Fusion3DGS:基于高斯斯喷涂的标签效率高的多模 3D 实例细分

Zhiyuan Wang^1,2, Chuang Luo^1,2, Jianping Zhang^3,4

¹School of Transportation and Logistics, Southwest Jiaotong University, Chengdu, 610031, China.

Scientific reports

|January 6, 2026

概括

Fusion3DGS只使用2D面具实现了高效的3D实例细分,减少了对昂贵3D数据的需求. 这种新的框架通过利用易于获得的RGB图像来增强嵌入式系统中的感知.

科学领域:

计算机视觉计算机视觉
机器人技术机器人技术机器人技术
机器学习机器学习

背景情况:

准确的3D实例细分对于嵌入式系统至关重要,但依赖于昂贵的3D点云注释.
由于数据采集成本,目前的方法在不同传感器和环境的可扩展性方面面临挑战.

研究的目的:

使用易于获得的2D数据开发一个标签效率高的框架来对3D实例进行细分.
解决当前感知系统中密集3D注释的瓶问题.

主要方法:

介绍了Fusion3DGS,这是一个端到端的框架,将3D高斯斯裂纹与2D-3D神经处理相结合.
利用多视图RGB图像与2D实例面具来优化一个紧的异构的高斯场景表示.
采用了闭塞意识的交叉注意力融合堆,例如推理,结合了重量共享锁定和染一致性目标.

主要成果:

从2D实例面具实现了标签效率高的3D实例细分,大大降低了注释要求.
通过染一致性,在遮蔽和不同视角下展示了改进的边界保真性.
通过使用广泛可用的RGB数据验证了该框架在大规模部署中的实用性.

结论:

通过克服密集3D数据的局限性,Fusion3DGS为3D实例细分提供了一个实用的解决方案.
该框架能够从二维监督中学习,这使得它可以扩展和适应各种嵌入式AI应用程序.

更多相关视频

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

相关概念视频

Tagging and Fusion Proteins

Tagging and Fusion Proteins

Proteins are involved in several cellular processes and biochemical reactions. Analyzing a specific protein of interest requires it to be isolated from the other proteins in the cell. This is achieved by overexpressing the specific gene in a suitable host to produce large quantities of the target protein. A tag or label is recombined with the gene to produce a fusion protein containing the target protein and the tag. The tags on these fusion proteins can then be used for easy detection and...