This course aims to provide a solid understanding of modern Computer Vision. It starts with essential backgrounds in image processing and classical vision methods, then transitions to contemporary learning-based techniques. Students will master core architectures including CNNs, Transformers, and generative models like GANs and Diffusion. Advanced modules explore detection, segmentation, and learning-based 3D vision. The course emphasizes problem-solving through a practical mini-project, encouraging students to apply these algorithms to real-world needs such as biomedical analysis or AR/VR. Students will finish the course ready to conduct independent research and develop innovative vision solutions.
Unlock more information by signing in with your HKUST account.