Seminar IN2107, which is open to Master students from "computer science", "games engineering", "robotics, cognition, and intelligence", and other programs. Please consult TUMonline or your study coordinator for more information.

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 include related deep-learning-based papers and consider how these methods might become real-time-capable in the future.

• Organizers: Christiane Sommer, Lukas Köstler
• Email: realtime3d-ss21@vision.in.tum.de (please address all requests to this address only!)
• Due to the current situation with the Coronavirus, the initial meeting will be online. The seminar and meetings with the supervisor will be online. We hope that the situation will improve such that this can be changed.

All information as well as the slides from the pre-meeting can be found here (password protected). The password is distributed during the preliminary meeting.

• Slides: PDF (If you missed the meeting, all necessary information is contained in the slides.)
• Date: February 2
• Time: 14:00 - 15:00
• Location: The meeting will be held online and more details can be found on TUMonline, s.t. the meeting can only be joined by TUM students
• Places will be assigned through the TUM matching system. A brief application by e-mail is necessary and the requirements are given during the preliminary meeting

• Day: Tuesday, approximately every second week (TBA)
• Time: 14:00 - 16:00
• Location: Zoom
• Each session will consist of two talks
• All talks are held in English