Lecture

Computer Vision: Image Formation and Transformation

Description

This lecture covers the fundamentals of image formation and transformation in computer vision. It begins with a discussion on the basic linear model of a camera, emphasizing the importance of projective geometry and the role of optics in capturing images. The instructor explains how different types of eyes in nature, such as pinhole and lens-based eyes, relate to camera models. The lecture then transitions to image transformations, detailing various mathematical transformations like affine and projective transformations, and their applications in aligning images. The concept of correspondences between images is introduced, highlighting the shift from handcrafted features to data-driven approaches using neural networks for finding correspondences. The lecture concludes with a discussion on dynamic perspectives in video, including motion sensing and optical flow, and the challenges of 3D reconstruction from 2D images. Overall, the lecture provides a comprehensive overview of the principles underlying image processing and computer vision.

About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.