Television technology has transitioned from black and white to color, from color to 16:9, and from 16:9 to high definition. Now that Hollywood and related industries are heavily investing in the space, there is a significant chance that the next move is going to be to three-dimensional (3D) TV. For this reason, de Aguiar’s monograph is an extremely timely publication.

The book is an extension of the author’s doctoral thesis in computer science. Its 16 chapters are grouped into four parts: Part 1, “Background and Basic Definitions,” Part 2, “Natural Animation of Digitized Models,” Part 3, “Towards Performance Capture Using Deformable Mesh Tracking,” and Part 4, “Processing Mesh Animations.”

The first part presents computer vision terminology and describes how camera images, kinematics, shape, and appearance are modeled in a computer, along with common algorithms that work on these models. Its chapters introduce interactive shape deformation and editing methods. The final chapter in this part presents the specific recording setup that was used in the author’s dissertation work.

Parts 2 to 4 constitute de Aguiar’s contributions to the field of computer graphics, as part of his doctoral work. His work reduces the time it takes to generate character animations, addresses the challenges of “passive performance capture of human actors wearing arbitrary everyday apparel[,]” and presents new “techniques for processing and modifying mesh animations[,]” as opposed to skeleton-based techniques. The author presents two mesh-based algorithms that simplify the overall character animation process, “three passive performance capture methods ... [that] employ a deformable model as underlying scene representation[,]” and two novel algorithms for processing mesh animations. As de Aguiar states in the summary, “the methods described in this book can be regarded as solutions to specific problems or important building blocks for a larger application.”

As expected from a monograph derived from a dissertation, the book presents high-quality research results, in a clear way. Unfortunately, when de Aguiar turned his doctoral thesis into a Springer book, he should have extended the scope to a broader target audience, by better positioning the work in the field; also, references to important work from important institutions, such as the Massachusetts Institute of Technology (MIT), are missing. Furthermore, he fails to provide a broader perspective of the field, perhaps one that would include other important 3D computer graphics applications, such as 3D tele-immersion and cultural heritage preservation. Also, the work focuses only on visual processing--it does not even mention more recent multimedia work on 3D modeling, such as acoustic and multimodal approaches. Therefore, the book will mainly interest scientists and future researchers in the field of 3D computer graphics modeling.