This 3D Computer Vision & Medical Imaging AI Course is designed to introduce learners to advanced topics in computer vision, focusing on 3D data processing, medical imaging, and generative AI workflows. It is suitable for students, researchers, and developers interested in AI, healthcare imaging, and 3D modeling.
The course begins with an introduction to modern 3D generative AI workflows, including tools like TRELLIS.2, which help streamline complex 3D content creation and processing. Learners will understand how generative models are applied in real-world 3D applications.
Students will then explore medical image registration techniques, including CT and MRI alignment using SimpleITK in Python. The course also explains non-rigid registration methods used in medical motion modeling, such as lung CT analysis.
In addition, learners will study 3D computer vision concepts like stereo vision reconstruction, point cloud processing, and Signed Distance Fields (SDF) for collision detection and spatial analysis. The training highlights how point cloud AI is becoming a powerful alternative to traditional computer vision methods.
By the end of this course, learners will be able to understand and apply 3D vision techniques, process medical imaging data, and work with ad
