CS 280A: Computer Vision — UC Berkeley
Automatic color image recovery from digitized glass plate photographs using multi-scale pyramid search technique.
Explore edge detection, image sharpening, hybrid images, and multiresolution blending using Laplacian stacks.
Manual and automatic image stitching using homography estimation, feature detection, and RANSAC for robust alignment.
3D scene reconstruction from multi-view images using machine learning, positional encoding, and volumetric rendering techniques.
Explore diffusion models for image generation, editing, and synthesis including text-to-image and visual anagrams.
Train flow matching models on MNIST with time and class conditioning for iterative image generation.