TUM-DLR Summer School 2017
October 4–6, 2017, at the JUFA Hotel Wangen, Allgäu.
Date and Venue
This year's TUM-DLR Summer School will take place at the JUFA Hotel Wangen - Sport-Resort, close to Lake Constance.
|Wednesday, October 4th|
|by 10:30||Arrival at Wangen & Check-In|
|10:30||Welcome & Instructions||Camp Nou|
|11:00||Poster Teasers||Camp Nou|
|14:00||Poster Session 1||Camp Nou|
|15:30||Poster Session 2||Camp Nou|
Prof. Vincent Lepetit: Deep Learning for 3D Localization
|Thursday, October 5th|
Bertrand Le Saux: Semantic Labeling of Remote Sensing Data, from 2D to 3D
|10:30||Workshop Session 1|
|Introduction to Python and Version Control with GIT||Camp Nou|
|Exploring Generative Adversarial Networks||Wembley|
|Friday, October 6th|
|9:00||Research "Meet & Greet"||Camp Nou |
|10:30||Workshop Session 2|
|Google Earth Engine||Camp Nou|
|Exploring the Potential of Geo-tagged Social Media Data in Geoscience||Wembley|
|14:30||Professor/Supervisor Input||Camp Nou|
|15:30||Closing and Feedback||Camp Nou|
|16:00||Check-Out & Departure|
This agenda is tentative and subject to change. You can import our Google Calendar (https://calendar.google.com/calendar/ical/surq4e6lor2j86lh0t49vafqrc%40group.calendar.google.com/public/basic.ics) in order to stay up-to-date.
Prof. Vincent Lepetit
Deep Learning for 3D Localization
The first part of the talk will describe a novel method for 3D object detection and pose estimation from color images only. We introduce a "holistic"’ approach that relies on a representation of a 3D pose suitable to Deep Networks and on a feedback loop. This approach, like many previous ones is however not sufficient for handling objects with an axis of rotational symmetry, as the pose of these objects is in fact ambiguous. We show how to relax this ambiguity with a combination of classification and regression. The second part will describe an approach bridging the gap between learning-based approaches and geometric approaches, for accurate and robust camera pose estimation in urban environments from single images and simple 2D maps.
Bertrand Le Saux, PhD
Semantic Labeling of Remote Sensing Data, from 2D to 3D
This talk will be about scene understanding with neural networks. Precisely, it starts from a brief introduction about classification of aerial and satellite images and the advent of deep learning for solving this task, then discusses various kinds of deep networks for dense semantic classification, fusion of heterogeneous data (especially with residual correction), and joint-learning with additional cartography. In a second part, it moves to 3D with semantic labeling of point clouds and presents SnapNet a multi-view convnet which can classify 3D from LiDAR or photogrammetry. It discusses various strategies for urban modeling or robotic exploration. Building on latest developments of the last years, we will see how it is now possible to semantize the world that surrounds us.
Introduction to Python and Version Control with GIT
Exploring Generative Adversarial Networks
Exploring the Potential of Geo-tagged Social Media Data in Geoscience
Google Earth Engine
On Thursday afternoon (4-7 pm), we booked 10 lanes at the
Seaside Bowling Center
Meistershofener Str. 14
Afterwards, we will have a joint buffet-style dinner there.
You can access further course material from our Google Drive folder.
For registration, please fill out this form.
Chair of Remote Sensing Technology
Professorship of Signal Processing in Earth Observation
Professorship of Photogrammetry and Remote Sensing
Chair of Cartography