An Invitation to 3-D Vision

Rating:
Summary: a must-have book for computer vision students & researchers
Review: The authors do an outstanding job of balancing theory and practice in this book. In particular, Ch. 11 (Step-by-Step Building of a 3-D Model from Images) is a gem. The new student of computer vision that finds Structure from Motion (SFM) daunting should read this chapter first to build motivation by means of seeing concrete examples.
What's most notable about this book is its thoroughness. The authors humbly get their hands dirty with crucial low-level matters like interest point detection and feature tracking. In Ch. 5 and 6 (calibrated and uncalibrated reconstruction) you'll get an excellent treatment of the necessary background in these areas, along with numerous new insights and `nuggets.' This is particularly true in their treatment of homographies. Ch. 2 has all the material on rigid body motion and the exponential map that students used to need to get from Murray, Li and Sastry, once again with substantial added value.
The exercises in all the chapters are very well thought out, and they -- together with the clearly written Algorithm Boxes -- greatly simplify the job of the instructor. (I am currently using this as the text for my graduate level class this quarter.) The appendices (especially the one on Linear Algebra) also help to make this a self-contained resource for SFM.
I haven't gotten into the material on multi-body motion and n>2 views, so I can't comment on those parts(...)In summary, this is a great book, well worth the money.