Block seminar for computer science and games engineering master students (IN2107).

Visual simultaneous localization and mapping (SLAM) or Structure from Motion (SfM) is a classical problem in computer vision. It has wide applications in autonomous navigation, virtual/augmented reality, 3D scanning etc. In this seminar, we will start by reviewing the classical approaches in the literature and then proceed to the more recent methods for SLAM and SfM. In particular, topics will range from monocular to stereo and RGB-D cameras, from static methods to dynamic settings, and from low-level feature-based algorithms to high-level semantics-oriented approaches. We will also look at shading-based reconstruction methods such as shape from shading and photometric stereo.

• Organizers: David Schubert, Christiane Sommer, Björn Häfner
• Email: realtime3d-ss20@vision.in.tum.de (please address all requests to this address only!)
• The seminar will be held block-wise on April 15th-16th.
• Due to the current situation with the Corona virus, the seminar will be held as an online-seminar. More information to follow.

All information as well as the slides from the pre-meeting can be found here (password protected).

• Days: Wednesday, April 15th and Thursday, April 16th
• Time: 9:00-17:00
• Location: 02.09.023
• There will be 6-7 talks per day.
• All talks are held in English.