Vector Visions: Introduction to Image Processing and AI for Designers
This course integrates computer vision and generative AI for students in architecture, urban design, sustainable design and related fields. It covers fundamental image processing and generative AI concepts like generative adversarial networks (GANs) and diffusion models.
Image of Abraham Lincoln as a matrix of pixel values. Image Credit: Thomas Smits
This course integrates computer vision and generative AI for students in architecture, urban design, sustainable design and related fields. It covers fundamental image processing and generative AI concepts like generative adversarial networks (GANs) and diffusion models. Through hands-on projects, students process and manipulate image data from buildings to urban landscapes. Students build a solid understanding of image processing and discover its crucial role in emerging AI technologies. By the end of the course, students will be able to apply these skills to real-world design challenges using tools such as Python, TensorFlow and OpenCV.
Prerequisites: None.