Master-Seminar - 3D Vision (IN2107)

Prof. Dr. Matthias Niessner & Dr. Justus Thies

Content

In this course, students will autonomously investigate recent research about 3D Scanning & Motion Capturing. Independent investigation for further reading, critical analysis, and evaluation of the topic are required. Each participant has to give a talk about a paper of the top tier conferences in this field (SIGGRAPH, SIGGRAPH ASIA, CVPR, ICCV, ECCV, ...). In addition to the talk we ask for a summary of the paper (minimum 2 pages).

The talks have to cover the following topics:

• face tracking / reconstruction
• facial reenactment (audio driven, video driven animation)
• body tracking / reconstruction
• hand tracking
• static / dynamic scene reconstruction
• scene understanding
• inverse rendering, material estimation, light estimation

Requirements

• The participants have to present their results in a talk, which should last 30 minutes.
• The semi-final slides (PDF) should be sent one week before the talk; otherwise, the talk will be canceled.
• A short report (approximately 2-3 pages in the ACM SIGGRAPH TOG format (acmtog)) should be prepared and sent within two weeks after the talk.
• When you send the report, please send the final slides (PDF) together.