Practical Course: Deep Learning for Spatial AI (10 ECTS)
Overview
This practical course aims at advanced students with prior knowledge of deep learning (e.g. Introduction to Deep Learning, IN2346), multi-view geometry (e.g. Computer Vision II, IN2228) or semantic understanding (e.g. Computer Vision III, IN2375). The goal of this course is to gain practical experience with state-of-the-art computer vision models and experiment with new ideas to address open real-world challenges in Spatial AI.
Organisers
News
- 28.01.2025: The capacity of the course is limited (max. 30 students). Please send us your CV and transcripts to dl4sai-ss25@vision.in.tum.de by February 20 (single compact PDF).
Dates
February 10, 11:00 | Preliminary meeting ( Slides) |
February 14-19 | Register in the matching system |
April 14, 11:00–12:00 | Project topics (in-person, 02.09.023) |
April 15-18 | Project matching |
May 19, 11:00–13:00 | Midterm presentations (in-person, 02.09.023) |
July 28, | Final presentations (in-person, 02.09.023) |
September 30 | Project reports due |
Course logistics
Course supervisors will initially offer peer-reviewed project ideas. The projects will focus on topics in Spatial AI, e.g. obtaining semantic and/or geometric knowledge from images or point clouds, such a camera/object pose estimation, video/panoptic segmentation. Each project will be assigned to a group of up to three students and supported by the project advisor. At the end of the course, the student groups will present their project results in class and submit a written report.
Prerequisites: IN2346, IN2228, IN2375 (or equivalent).