Computational Imaging of Dynamic Scenes from Optical Scattering Data

该项目是根据光学散射数据近乎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基于物理模型(辐射传输)的蒙特卡罗采样和机器学习算法，以快速逼近逆问题的解。研究方案中的应用提供了探索光学成像(3D断层成像)的基本原理、用于实时解决复杂问题的随机代数以及用于学习基于景观地形数据的低维弥散模型的物理启发的神经网络的可能性。

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.