Image Stitching

This is the final project for CSE 5524: Computer Vision for Human-Computer Interaction at The Ohio State University.

This project explores how computer vision techniques can be used to generate panoramic images by stitching together photos with overlapping views. By detecting keypoints, aligning perspectives, and blending boundaries, the system reconstructs a larger, seamless image from multiple inputs.

Rather than using pre-built panorama functions, we implemented the full pipeline from scratch using SIFT for feature matching, RANSAC for robust transformation estimation, and custom warping and blending techniques to create the final output.