Dense Image Correspondences for Computer Vision

1. Front Matter

   Pages i-xii

   PDF

2. Establishing Dense Correspondences

   1. Front Matter

      Pages 1-1

      PDF

   2. Introduction to Dense Optical Flow

      • Ce Liu

      Pages 3-14

   3. SIFT Flow: Dense Correspondence Across Scenes and Its Applications

      • Ce Liu, Jenny Yuen, Antonio Torralba

      Pages 15-49

   4. Dense, Scale-Less Descriptors

      • Tal Hassner, Viki Mayzels, Lihi Zelnik-Manor

      Pages 51-70

   5. Scale-Space SIFT Flow

      • Weichao Qiu, Xinggang Wang, Xiang Bai, Alan Yuille, Zhuowen Tu

      Pages 71-82

   6. Dense Segmentation-Aware Descriptors

      • Eduard Trulls, Iasonas Kokkinos, Alberto Sanfeliu, Francesc Moreno-Noguer

      Pages 83-107

   7. SIFTpack: A Compact Representation for Efficient SIFT Matching

      • Alexandra Gilinsky, Lihi Zelnik-Manor

      Pages 109-133

   8. In Defense of Gradient-Based Alignment on Densely Sampled Sparse Features

      • Hilton Bristow, Simon Lucey

      Pages 135-152

3. Dense Correspondences and Their Applications

   1. Front Matter

      Pages 153-153

      PDF

   2. From Images to Depths and Back

      • Tal Hassner, Ronen Basri

      Pages 155-172

   3. Depth Transfer: Depth Extraction from Videos Using Nonparametric Sampling

      • Kevin Karsch, Ce Liu, Sing Bing Kang

      Pages 173-205

   4. Nonparametric Scene Parsing via Label Transfer

      • Ce Liu, Jenny Yuen, Antonio Torralba

      Pages 207-236

   5. Joint Inference in Weakly-Annotated Image Datasets via Dense Correspondence

      • Michael Rubinstein, Ce Liu, William T. Freeman

      Pages 237-278

   6. Dense Correspondences and Ancient Texts

      • Tal Hassner, Lior Wolf, Nachum Dershowitz, Gil Sadeh, Daniel Stökl Ben-Ezra

      Pages 279-295

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.

• Annotation Propagation
• Data Driven
• Dense Correspondence Estimation
• Dense Correspondences
• Dense Pixel Matching
• Dense SIFT
• Depth-transfer
• Example Based
• Label-transfer
• SIFT-Flow
• Scale-less SIFT

• The Open University of Israel, Raanana, Israel

  Tal Hassner

• Google Research, Cambridge, USA

  Ce Liu

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.

Policies and ethics