This 3D Computer Vision course provides a practical introduction to advanced visual computing techniques used in AI, robotics, autonomous systems, and medical imaging. The course focuses on point cloud processing, 3D reconstruction, mesh analysis, and modern AI workflows using Python libraries such as Open3D, PyVista, and SimpleITK.

The series begins with the fundamentals of 3D computer vision, including point cloud processing, mesh handling, and voxel grid generation. Learners then explore surface reconstruction methods and signed distance fields (SDF) for collision detection and geometric analysis.

The course also covers important registration algorithms such as RANSAC, ICP, and Coherent Point Drift for aligning 3D point clouds and performing deformable non-rigid registration. These methods are widely used in robotics, AR/VR, and autonomous driving systems.

Advanced topics include stereo vision reconstruction pipelines, PointNet-based segmentation, and point cloud AI techniques inspired by modern autonomous vehicle systems. The course also introduces medical image registration using CT and MRI data with SimpleITK, helping learners understand healthcare imaging workflows.

Additionally, learners explore modern generative AI workflows for 3D modeling and scene generation. By the end of the course, learners gain hands-on experience building advanced 3D computer vision systems using real-world datasets and AI-powered techniques.