Dense Image Correspondences for Computer Vision

• Συγγραφή απο Οργανισμό/Αρχή: SpringerLink (Online service)
• Άλλοι συγγραφείς: Hassner, Tal (Επιμελητής έκδοσης), Liu, Ce (Επιμελητής έκδοσης)
• Μορφή: Ηλεκτρονική πηγή Ηλ. βιβλίο
• Γλώσσα: English
• Έκδοση: Cham : Springer International Publishing : Imprint: Springer, 2016.
• Έκδοση: 1st ed. 2016.
• Θέματα: Engineering.; Artificial intelligence.; Image processing.; Electrical engineering.; Signal, Image and Speech Processing.; Image Processing and Computer Vision.; Artificial Intelligence (incl. Robotics).; Communications Engineering, Networks.

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 applic...

Πίνακας περιεχομένων:

• Introduction to Dense Optical Flow
• SIFT Flow: Dense Correspondence across Scenes and its Applications
• Dense, Scale-Less Descriptors
• Scale-Space SIFT Flow
• Dense Segmentation-aware Descriptors
• SIFTpack: A Compact Representation for Efficient SIFT Matching
• In Defense of Gradient-Based Alignment on Densely Sampled Sparse Features
• From Images to Depths and Back
• DepthTransfer: Depth Extraction from Video Using Non-parametric Sampling
• Joint Inference in Image Datasets via Dense Correspondence
• Dense Correspondences and Ancient Texts.