Seminar: Computer Vision and Deep Learning for Autonomous Driving

PD Dr. Federico Tombari, Prof. Nassir Navab, Fabian Manhardt, Johanna Wald

Type: Seminar Module IN0014
SWS: 2+0
ECTS: 5 Credits
Location: CAMP Seminar Room, 03.13.010
Time: Wednesday, 10.00am-11.30am
Course Language: English

Announcements

• The slides of the preliminary meeting are available.
• If interested in registering for the Seminar, you can send us your motivation letter (plus relevant courses that you have taken) at cvdlad-w18[at]googlegroups.com. Please note that the official application has to be done via the TUM Matching System.
  

Introduction

• The seminar includes a selection of the most recent and relevant papers in the field of computer vision and deep learning aimed at autonomous driving.
• Papers are selected to cover different aspects of the topic:
  • (Lightweight) Semantic Segmentation
  • Scene Understanding
  • Multi-modal sensor fusion
  • SLAM and 3D reconstruction
  • Joint depth and visual odometry prediction
  • Synthetic dataset creation
  • Car simulators
  • Semi-supervised large-scale dataset annotations
  • Trajectory planning and lane change prediction
• The full list of papers will be available a few weeks before the beginning of the semester.

Registration

• Preliminary Meeting: Jun. 21st, 1pm, in room: CAMP Seminar Room, 03.13.010
• Registrations will be handled through the TUM Matching Platform.

Requirements

In this Master Seminar (formerly Hauptseminar), each student is asked to select one paper from a list. In order to successfully complete the seminar, participants have to fulfill these requirements:

• Presentation: The selected paper is presented to the other participants (20 minutes presentation 10 minutes questions). Use the CAMP templates for PowerPoint camp-tum-jhu-slides.zip, or Latex: CAMP-latex-template.
• Written Report: A document of maximum 8 pages is written and submitted one week after the presentation. Please download and use the llncs2e.zip Latex template.
• Attendance: Participants have to participate actively in all seminar sessions.

The students are required to attend each seminar presentation which will be held during this course. Each presentation is followed by a discussion and everyone is encouraged to actively participate. The report must include all references used and must be written completely in your own words. Copy and paste will not be tolerated. Both report and presentation have to be done in English.

List of Topics and Material

A list of papers will be announced here.

Nr	Authors	Title	Topic	Conference	Link	Tutor	Student
1	A. Paszke et al.	ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation	Lightweight CNNs	Arxiv 2018	link	Nikolas Brasch	Egor Labintcev
1	R. Mahjourian et al.	Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints	Depth/Odomoetry Prediction	CVPR 2018	link	Nikolas Brasch	Jan-Hendrik Neudeck
2	R. Wang et al.	Stereo DSO: Large-Scale Direct Sparse Visual Odometry with Stereo Cameras	SLAM	ICCV 2017	link	Jakob Mayr	Sandeep Kumar
2	S. Brahmbhatt et al.	Geometry-Aware Learning of Maps for Camera Localization	SLAM	CVPR 2018	link	Markus Herb	Mubashir Hanif
3	Y. Zhou et al.	VoxelNet?: End-to-End Learning for Point Cloud Based 3D Object Detection	3D Object Detection	CVPR 2018	link	Johanna Wald	Sascha Geringer
3	D. Xu et al.	PointFusion?: Deep Sensor Fusion for 3D Bounding Box Estimation	3D Object Detection	CVPR 2018	link	Markus Herb	Simon Weigl
4	Huang et al.	The ApolloScape? Dataset for Autonomous Driving	Large-scale dataset annotation	Arxiv 2018	link	Johanna Wald	Alessio Tofani
4	A. Dosovits.	CARLA: An Open Urban Driving Simulator	Car simulators	CoRL? 2017	link	Artem Savkin	Josefine Gaßner
5	M. Liu et al.	Unsupervised Image-to-Image Translation Networks	GANs for synthetic dataset generation	NIPS 2017	link	Artem Savkin	Muhammad Ferjad Naeem
5	T.-C. Wang et al.	High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs	GANs for synthetic dataset generation	CVPR 2018	link	Jakob Mayr	Tsuyoshi Beheim
6	Vemula et al.	Social Attention: Modeling Attention in Human Crowds	Trajectory prediction	ICRA 2018	link	Oliver Scheel	Ali Kareem Raja
6	F. Codevilla et al.	End-to-end Driving via Conditional Imitation Learning	Trajectory prediction	ICRA 2018	link	Oliver Scheel	Florian Ölsner

Schedule

The schedule for the paper presentations will be announced here during the semester. Each student is required to attend all presentations.

Date	Time	Place	Speaker	Topic	Invited External Talk
Wed 17.10.2018	10:00 - 11:30	3.13.010, Seminarraum	Federico and tutors	Introductory meeting
Wed 24.10.2018	10:00 - 11:30	3.13.010, Seminarraum	Egor Labintcev Jan-Hendrik Neudeck	Lightweight CNNs Depth/Odometry Prediction	A. Pasternak, Apex.AI
Wed 07.11.2018	10:00 - 11:30	3.13.010, Seminarraum	Sandeep Kumar Mubashir Hanif	SLAM	M. Herb, Audi
Wed 21.11.2018	10:00 - 11:30	3.13.010, Seminarraum	Sascha Geringer Simon Weigl	3D Object Detection	D. Zikic, Lyft
Wed 28.11.2018	10:00 - 11:30	3.13.010, Seminarraum	Alessio Tofani Josefine Gaßner	Large-scale dataset annotation Car simulators	J. Jamaszyk, Nvidia
Wed 05.12.2018	10:00 - 11:30	3.13.010, Seminarraum	Muhammad Ferjad Naeem Tsuyoshi Beheim	GANs for synthetic dataset generation	L. Schwarz, BMW
Wed 12.12.2018	10:00 - 11:30	3.13.010, Seminarraum	Ali Kareem Raja Florian Ölsner	Trajectory prediction	A. Abramov, Continental
Wed 16.01.2019	10:00 - 11:30	3.13.010, Seminarraum		Backup date