Seminar: Computer Vision and Deep Learning for Autonomous Driving

PD Dr. Federico Tombari, Helisa Dhamo, Shun-Cheng Wu, Yida Wang, Yanyan Li
Type: Seminar Module IN0014
SWS: 2+0
ECTS: 5 Credits
Location: CAMP Seminar Room, 03.13.010
Time: tba
Course Language: English

Announcements

• You can submit your motivation letter via email at: cvdlad-w19@googlegroups.com
• Preliminary Meeting: July 19th, 3pm, in room: CAMP Seminar Room, 03.13.010 slides

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.
• Blog Post: Will be clarified in the first session.
• 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 blog post must include all references used and must be written completely in your own words. Copy and paste will not be tolerated. Both blog post 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	Liang et al.	Multi-Task Multi-Sensor Fusion for 3D Object Detection	3D Object Detection	CVPR 2019	paper	Nikolas Brasch	Maximilian M
2	Ku et al.	Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction	6D Pose Estimation	CVPR 2019	paper	Mahdi Saleh	Maximilian K
3	Voigtlaender et al.	MOTS: Multi-Object Tracking and Segmentation	2D Tracking and Segmentation	CVPR 2019	paper	Nikolas Brasch	Ege
4	Casser et al.	Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos	Depth Prediction	AAAI 2019	paper	Markus Herb	Evin
5	Li et al.	Stereo Vision-based Semantic 3D Object and Ego-motion Tracking for Autonomous Driving	Ego-Motion & 3D Object Tracking	ECCV 2018	paper	Markus Herb	Emanuel
6	Behley et al.	Efficient Surfel-Based SLAM using 3D Laser Range Data in Urban Environments	LIDAR SLAM & Dense Reconstruction	RSS 2018	paper	Markus Herb	Ivan
7	Gupta et al.	Social GAN	Trajectory Prediction	CVPR 2018	paper	Oliver Scheel	Mehmet
8	Cui et al.	Multimodal Trajectory Predictions for Autonomous Driving Using Deep Convolutional Networks	Trajectory Prediction	ICRA 2019	paper	Oliver Scheel	Artemii
9	Bansal et al.	ChauffeurNet?: Learning to Drive by Imitating the Best and Synthesizing the Worst	End-to-End Driving	RSS 2019	paper	Oliver Scheel	Alexander
10	Luo et al.	Taking A Closer Look at Domain Shift:Category-level Adversaries for Semantics Consistent Domain Adaptation	Domain Adaptation	CVPR 2019	paper	Artem Savkin	Mert
11	Fu et al.	Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping	Domain Adaptation	CVPR 2019	paper	Artem Savkin	Erkam
12	Li at al.	Attention-guided Unified Network for Panoptic Segmentation	2D Panoptic Segmentation	CVPR 2019	paper	Yanyan Li	Lukas

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
Fri, October 18, 2019	16:00-18:00	3.13.010, Seminarraum	Federico	Introductory talk slides
Fri, November 8, 2019	16:00-18:00	3.13.010, Seminarraum	Maximilian M Maximilian K Ege	Object Detection, Pose Estimation and Tracking	A. Braun (Bosch)
Fri, November 29, 2019	16:00-18:00	3.13.010, Seminarraum	Evin Emanuel Ivan	Depth prediction, SLAM and Reconstruction	O. Lazarevych (Lyft)
Fri, December 13, 2019	16:00-18:00	3.13.010, Seminarraum	Mehmet Artemii Alexander	Trajectory prediction and End-to-End Driving	N. Kose Cihangir (Intel)
Fri, January 17, 2020	16:00-18:00	3.13.010, Seminarraum	Mert Erkam Lukas	Domain Adaptation and Panoptic Segmentation	M.-A. Nikouei Mahani (BMW)