Dense Image Correspondences for Computer Vision

ISBN-13: 9783319230474 / Angielski / Twarda / 2015 / 295 str.

Tal Hassner; Ce Liu

Opis

Dense Image Correspondences for Computer Vision

Spis treści

Introduction.- Part I – Establishing dense correspondences.- Classic dense-correspondence estimation – Horn & Schunck, Lucas & Kanade, and beyond.- SIFT-Flow - Correspondences beyond same-scene image pairs.- SIFTS and Scales – Correspondences with scale differences.- Patchmatch – Fast correspondence estimation.- SIFT-Pack – Same SIFTs for a smaller price.- Segmentation-Flow.- Part II – Dense correspondences and their applications.- Depth by example – From images to depth and back.- Label-transfer.- Depth-transfer.- Image similarity.- Dense-Flow and ancient texts.- Computational photography – super-resolution and de-noising.- Biometrics.- Image hallucination.- Part III – Analyzing images as videos.- Annotation propagation.- Object discovery and co-segmentation.- Appendix.

O autorze

Prof. Tal Hassner is a faculty member of the Department of Mathematics and Computer Science, The Open University of Israel, Israel. Ce Liu is a Researcher with Google.

Blurb

This book describes the fundamental building-block of many new computer vision systems: dense and robust correspondence estimation. Dense correspondence estimation techniques are now successfully being used to solve a wide range of computer vision problems, very different from the traditional applications such techniques were originally developed to solve. This book introduces the techniques used for establishing correspondences between challenging image pairs, the novel features used to make these techniques robust, and the many problems dense correspondences are now being used to solve. The book provides information to anyone attempting to utilize dense correspondences in order to solve new or existing computer vision problems. The editors describe how to solve many computer vision problems by using dense correspondence estimation. Finally, it surveys resources, code, and data necessary for expediting the development of effective correspondence-based computer vision systems.

 

·         Provides in-depth coverage of dense-correspondence estimation

·         Covers both the breadth and depth of new achievements in dense correspondence estimation and their applications

·         Includes information for designing computer vision systems that rely on efficient and robust correspondence estimation