Dense Image Correspondences for Computer Vision

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.

Table of Contents

Part I Establishing Dense Correspondences
Chapter 1 Introduction to Dense Optical Flow
Chapter 2 SIFT Flow: Dense Correspondence Across Scenes and Its Applications
Chapter 3 Dense, Scale-Less Descriptors
Chapter 4 Scale-Space SIFT Flow
Chapter 5 Dense Segmentation-Aware Descriptors
Chapter 6 SIFTpack: A Compact Representation for Efficient SIFT Matching
Chapter 7 In Defense of Gradient-Based Alignment on Densely Sampled Sparse Features

Part II Dense Correspondences and Their Applications
Chapter 8 From Images to Depths and Back
Chapter 9 Depth Transfer: Depth Extraction from Videos Using Nonparametric Sampling
Chapter 10 Nonparametric Scene Parsing via Label Transfer
Chapter 11 Joint Inference in Weakly-Annotated Image Datasets via Dense Correspondence
Chapter 12 Dense Correspondences and Ancient Texts