Computational Imaging of Dynamic Scenes from Optical Scattering Data

根据光学散射数据对动态场景进行计算成像

• 批准号: 2733996
• 金额: --
• 依托单位: University of Edinburgh
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2022
• 资助国家: 英国
• 起止时间: 2022 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2733996
• 关键词: Computational; Imaging; Dynamic; Scenes; Optical

The project is to reconstruct three-dimensional images of dynamic scenes from optical scattering data in near real-time. The image reconstruction and rendering tasks combine Monte Carlo sampling of physics-based models (radiative transport) and machine learning algorithms for the rapid approximation of the solution of the inverse problem. The application in the research proposal offers the possibility of exploring the fundamentals of optical imaging (3D tomography), randomised algebra for solving complex problems in real-time and physics-inspired neural networks for learning a low-dimensional dispersion model "on-the-fly" based on landscape topography data.

该项目是从光学散射数据中近实时地重建动态场景的三维图像。图像重建和渲染任务结合了联合收割机对基于物理的模型（辐射传输）的蒙特卡罗采样和机器学习算法，以快速近似逆问题的解。在研究提案中的应用提供了探索光学成像（3D断层扫描）的基础知识，用于实时解决复杂问题的随机代数和物理启发的神经网络的可能性，用于学习基于景观地形数据的低维色散模型“实时”。