Modern Techniques and Applications for
Real-Time Non-rigid Registration
Sofien Bouaziz
EPFL
Andrea Tagliasacchi
University of Victoria
Hao Li
USC/ICT
Mark Pauly
EPFL
Abstract. Registration algorithms are an essential component of many computer
graphics and computer vision systems. With recent technological advances in RGB-
D sensors (color plus depth), an active area of research is in techniques combining
color, geometry, and learnt priors for robust real-time registration. The goal of
this course is to introduce the mathematical foundations and theoretical explana-
tion of registration algorithms, in addition to the practical tools to design systems
that leverage information from RGBD devices. We present traditional methods
for correspondence computation derived from geometric first principles, along with
modern techniques leveraging pre-processing of annotated datasets (e.g. deep neu-
ral networks). To illustrate the practical relevance of the theoretical content, we
discuss applications including static and dynamic scanning/reconstruction as well
as real-time tracking of hands and faces. An up-to-date version of the course notes,
as well as slides and source code can be found at http://gfx.uvic.ca/teaching/
registration.
Course Syllabus (SIGGRAPH Asia’16)
1.1 (5min, Tagliasacchi) Introduction, motivation and sensing hardware
1.2 (20min, Tagliasacchi) Hausdorff distances, rigid registration, ICP
1.3 (20min, Tagliasacchi) Robust registration, articulated registration
(10 minutes break)
2.1 (20min, Li) Non-rigid registration and face tracking
2.2 (20min, Li) Correspondences with Convolutional Neural Networks
2.3 (10min, Li) Conclusions and Q&A
Permission to make digital or hard copies of part or all of this work for personal or
classroom use is granted without fee provided that copies are not made or distributed
for profit or commercial advantage and that copies bear this notice and the full citation
on the first page. Copyrights for third-party components of this work must be honored.
For all other uses, contact the Owner/Author. Copyright is held by the owner/author(s).
SA ’16 Courses, December 05-08, 2016, Macao. ACM 978-1-4503-4538-5/16/12 http:
//dx.doi.org/10.1145/2988458.2988490
1
剩余24页未读，继续阅读
资源评论
