TeachingSs21CVDLAD

Chair for Computer Aided Medical Procedures & Augmented Reality
Lehrstuhl für Informatikanwendungen in der Medizin & Augmented Reality

Seminar: Computer Vision and Deep Learning for Autonomous Driving

PD Dr. Federico Tombari, Nikolas Brasch, Shun-Cheng Wu, Mahdi Saleh
Type: Seminar Module IN0014
SWS: 2+0
ECTS: 5 Credits
Location: Zoom meeting
Time: tba
Course Language: English

Announcements

  • You can submit your motivation letter via email.
  • Preliminary Meeting: *February 1st, 10:00-10:30am, slides
  • All sessions will be held over Zoom

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:
    • Semantic Segmentation
    • 3D Scene Understanding
    • Multi-modal sensor fusion
    • SLAM and 3D reconstruction
    • 6D object pose estimation / 3D object recognition
    • Joint depth and visual odometry prediction
    • Synthetic dataset creation
    • Generative models for sym-to-real
    • 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

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 Guizilini et al. 3D Packing for Self-Supervised Monocular Depth Estimation Monocular depth estimation CVPR 2020 paper Stefano Gasperini Lucas
2 Hidalgo-Carrio et al. Learning Monocular Dense Depth from Events Depth from Event Cameras 3DV 2020 paper Markus Herb Maximilian
3 Zeng et al. PnPNet?: End-to-End Perception and Prediction with Tracking in the Loop Detection, Tracking and Prediction CVPR 2020 paper Nikolas Brasch Rafid
4 Yin et al. Center-based 3D Object Detection and Tracking 3D Object Detection and Tracking CVPR 2021 paper Alexander Lehner Halil
5 Li et al. SIENet: Spatial Information Enhancement Network for 3D Object Detection from Point Cloud 3D Object Detection CVPR 2021 paper Mahdi Saleh Max
6 Tu et al. Physically Realizable Adversarial Examples for LiDAR? Object Detection Adversarial Augmentation CVPR 2020 paper Alexander Lehner Mohammed
7 Hong et al. LiDAR?-based Panoptic Segmentation via Dynamic Shifting Network LiDAR? panoptic segmentation CVPR 2021 paper Stefano Gasperini Zhixiong
8 Sarlin et al. Back to the Feature: Learning Robust Camera Localization from Pixels to Pose Localization CVPR 2021 paper Markus Herb Lixing
9 Lin et al. Loam-livox: A fast, robust, high-precision LiDAR? odometry and mapping package for LiDARs? of small FoV? SLAM/Reconstruction ICRA 2020 paper Yanyan Li Markus
10 Kong et al. Semantic Graph Based Place Recognition for 3D Point Clouds Relocalization IROS 2020 paper Nikolas Brasch Ilia
11 Yang et al. FDA: Fourier Domain Adaptation for Semantic Segmentation Domain Adaptation CVPR 2020 paper Artem Savkin Zeynep
12 Chen et al. Contrastive Syn-to-Real Generalization Domain Adaptation ICRL 2021 paper Artem Savkin Eddie

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
Mon, February 1, 2021 10:00-10:30 Zoom Federico Tombari Preliminary meeting slides  
Fri, April 16, 2021 15:00-17:00 Zoom Federico Tombari Introductory session slides  
Fri, April 23, 2021 15:00-17:00 Zoom Lucas, Maximilian, Rafid Student presentations  
Fri, May 07, 2021 15:00-17:00 Zoom Halil, Max, Mohammed Student presentations Sebastian Huch
Indy Autonomous Challenge
TUM
Fri, May 28, 2021 15:00-17:00 Zoom Zhixiong, Lixing, Markus Student presentations Francesco Ferroni
ArgoAI
Fri, June 18, 2021 15:00-17:00 Zoom Ilia, Zeynep, Eddie Student presentations Oliver Beck
CARIAD (Volkswagen Group)
Fri, July 09, 2021 15:00-17:00 Zoom   Backup  


TeachingForm
Title: Computer Vision and Deep Learning for Autonomous Driving
Professor: PD Dr. Federico Tombari
Tutors: Nikolas Brasch, Shun-Cheng Wu, Mahdi Saleh,
Type: Hauptseminar
Information: Hauptseminar, SWS: 2, ECTS: 5
Term: 2021SoSe
Abstract:  


Edit | Attach | Refresh | Diffs | More | Revision r1.12 - 30 Apr 2021 - 11:16 - NikolasBrasch

Lehrstuhl für Computer Aided Medical Procedures & Augmented Reality    rss.gif