This course covers advanced and recent geometric modeling and generation techniques in computer graphics. Our focus will be on the acquisition, representation, processing, analysis, and synthesis of 3D shapes, with applications to real-time 3D graphics, generative AI, design and manufacturing, as well as 3D machine vision and robotics. We will cover a variety of 3D representations including polygonal meshes, point clouds, voxels, multi-view geometries, neural fields, as well as structured representations. Both classical and modern-day learning-based approaches will be studied. This field is fast evolving with many interesting problems and much aspiration for application development and future research, e.g., in spatial and embodied AI, geometric deep learning, computational design, and creative arts and modeling. Basic mathematical concepts and tools necessary to understand the course will be presented depending on students background. Programming experience in computer graphics (CMPT 363 or equivalent) and machine learning (Python, C++) would be required. This course will be cross-listed with CMPT 764.
Course Topics: (not necessarily covered in that order):
Grading:
One midterms (30%), one assignment (20%), and a final project (50%)
References:
Interests in the topic; no obvious symptoms of math phobia. Programming experience in computer graphics (CMPT 361 or equivalent) and machine learning (Python, C++) would be required.