This repository contains codes & report for four homeworks in CS172.

• Reproduced Poisson image editing by Patrick Pérez, Michel Gangnet, and Andrew Blake in ACM SIGGRAPH 2003.

• Dataset: the Caltech 256 dataset.
• Image representation: Bag of Features, Spatial Pyramids Matching.
• Image classification: Support Vector Machine.

• Dataset: self-collected pictures of ShanghaiTech.
• Feature extraction: SURF.
• Self-implemented robust matching and RANSAC.
• Stitching by cv2.warpPerspective().

• Reproduced Eigen et al.’s NIPS 2014 paper: Depth Map Prediction from a Single Image using a Multi-Scale Deep Network.