Computer Vision

Catalog description

This course covers the foundations of computer vision, from image formation and filtering through modern deep learning approaches for recognition, generation, and 3D understanding. Topics include image processing and linear filtering, edge detection, image pyramids, neural networks, convolutional neural networks, transformers, object recognition, generative models, 3D reconstruction, motion estimation, and vision-language models. Students develop both mathematical foundations and practical skills through homework and a final project. Prerequisite(s): AIM 5005 , AIM 5007 , and COM 5323 .