Seminar: Computer Vision and Deep Learning for Autonomous Driving

PD Dr. Federico Tombari, Fabian Manhardt, Helisa Dhamo, Shun-Cheng Wu, Manuel Nickel

Type: Seminar Module IN0014
SWS: 2+0
ECTS: 5 Credits
Location: CAMP Seminar Room, 03.13.010
Time: Monday, 4.00pm-5.30pm
Course Language: English

Announcements

• PLEASE NOTE: The last session of the seminar is rescheduled for 22.07.2019!
• Preliminary Meeting: Jan. 28th, 4pm, in room: CAMP Seminar Room, 03.13.010
  The slides can be found here
• If interested in registering for the Seminar, you can send your motivation letter (plus relevant courses that you have taken) to cvdlad-sose19[at]googlegroups.com until Feb. 14th.
  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

• 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	Li et al.	UnDeepVO?: Monocular Visual Odometry through Unsupervised Deep Learning	monoDepth, SLAM	ICRA 2018	paper	Jakob Mayr	Maximilian
1	Dube et al.	SegMap?: 3D Segment Mapping using Data-Driven Descriptors	SLAM	RSS 2018	paper	Markus Herb	Friederike
1	Yang et al.	Deep Virtual Stereo Odometry: Leveraging Deep Depth Prediction for Monocular Direct Sparse Odometry	SLAM	ECCV 2018	paper	Markus Herb	Sami
2	Li et al.	Weakly- and Semi-Supervised Panoptic Segmentation	Semantic Segmentation	ECCV 2018	paper	Niko Brasch	Stanislav
2	Sandler et al.	MobileNetV2?: Inverted Residuals and Linear Bottlenecks	Lightweight CNNs	CVPR 2018	paper	Niko Brasch	Maja
2	Manhardt et al.	ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape	Object Pose Estimation	CVPR 2019	paper	Fabian Manhardt	Moiz
3	Wang et al.	Video-to-Video Synthesis	GAN / Synthetic Data	NIPS 2018	paper	Artem Savkin	Juan Jose
3	Qi et al.	Semi-parametric Image Synthesis	GAN / Synthetic Data	CVPR 2018	paper	Artem Savkin	Rajdeep
3	Tsai et al.	Learning to Adapt Structured Output Space for Semantic Segmentation	GAN / Synthetic Data	CVPR 2018	paper	Artem Savkin	Aulona
4	Maqueda et al.	Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Cars	Imitation Learning	CVPR 2018	paper	Jakob Mayr	Paul
4	Isele et al.	Navigating Occluded Intersections with Autonomous Vehicles using Deep Reinforcement Learning	Reinforcement Learning	ICRA 2018	paper	Oliver Scheel	Mansoor
4	Alahi et al.	Social LSTM	Trajectory Prediction	CVPR 2016	paper	Oliver Scheel	Chuxuan

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
Mo 28.01.2019	16:00 - 17:30	3.13.010, Seminarraum	Federico and tutors	Kickoff meeting
Mo 29.04.2019	16:00 - 18:00	3.13.010, Seminarraum	Federico	Introductory talk	-
Mo 13.05.2019	16:00 - 18:00	3.13.010, Seminarraum	Maximilian, Friederike, Sami	monoDepth / SLAM	F. Ferroni (AID)
Mo 03.06.2019	16:00 - 18:00	3.13.010, Seminarraum	Stanislav, Maja, Moiz	Scene Understanding / Network Compression	C. Unger (BMW)
Mo 24.06.2019	16:00 - 18:00	3.13.010, Seminarraum	Juan Jose, Rajdeep, Aulona	GANs / Synthetic Data	F. Petit (Blickfeld)
Mo 22.07.2019	16:00 - 18:00	3.13.010, Seminarraum	Paul, Mansoor, Chuxuan	Reinforcement Learning / Trajectory Prediction	S. Ramos (Zenuity)