Hauptseminar/Master Seminar:
Recent Trends in 3D Computer Vision and Deep Learning

PD Federico Tombari, Prof. Nassir Navab, Iro Laina, Helisa Dhamo

Course number: Module IN4826
Type: Advanced Seminar Course Module IN8901
Type: Master Seminar Module IN2107
Type: Seminar Module IN0014
SWS: 2+0
ECTS: 5 Credits
Location: TBD
Time: TBD
Course Language: English

Announcements

• To express your interest for the seminar, you can send us your motivation letter/email (including relevant courses that you have taken) at rt3dcvdl-w18|[at]|googlegroups.com, until 05.07.2018.
  
• Preliminary meeting: Thursday, 28.06.2018 at 13:15. Location: 03.13.010
  
  

Introduction

• The Seminar Course concerns recent advances in the field of 3D Computer Vision and Deep Learning. The Seminar will propose a list of recent scientific articles related to the main current research topics in the field, such as 3D keypoint detection and description, point cloud matching and registration, 3D object recognition and classification, SLAM, 3D reconstruction, 3D object pose estimation and tracking, depth prediction, 3D scene understanding.

Registration

• The registration will be performed through the TUM Matching Platform.

Requirements

In this Master Seminar, 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

Authors	Title	Conference	Link	Tutor	Student
Su et al.	SPLATNet: Sparse Lattice Networks for Point Cloud Processing	CVPR 2018	paper	Mahdi Saleh	Peter N.
Liu et al.	Learning Scene Flow in 3D Point Clouds	arXiv 2018	paper	Johanna Wald	Rahul B.
Rethage et al.	Fully-Convolutional Point Networks for Large-Scale Point Clouds	ECCV 2018	paper	Fatemeh Alidoost	Giulia M.
Bloesch et al.	CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAM	CVPR 2018	paper	Benjamin Busam	Hooriya A.
Henriques and Vedaldi	MapNet: An Allocentric Spatial Memory for Mapping Environments	CVPR 2018	paper	Iro Laina	Abinav V.
Das et al.	Embodied Question Answering	CVPR 2018	paper	Iro Laina	Sumant D.
Slavcheva et al.	SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-rigid Motion	CVPR 2018	paper	Patrick Ruhkamp	Tim P.
Tusliani et al.	Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene	CVPR 2018	paper	Helisa Dhamo	Abhishek
Song et al.	Semantic Scene Completion from a Single Depth Image	CVPR 2017	paper	Yida Wang	Behiye A.
Yu et al.	Generative Image Inpainting with Contextual Attention	CVPR 2018	paper	Helisa Dhamo	Aashish T.
Tekin et al.	Real-Time Seamless Single Shot 6D Object Pose Prediction	CVPR 2018	paper	Yongheng Zhao	Shervin D.
Pavlakos et al.	6-DoF Object Pose from Semantic Keypoints	ICRA 2017	paper	Ghazal Ghazaei	Hyunjun J.
Güler et al.	Densepose: Dense human pose estimation in the wild	CVPR 2018	paper	Huseyin Coskun	Abdul M.
Xu et al.	Attention-Aware Compositional Network for Person Re-identification	CVPR 2018	paper	Bharti Munjal	Haydar S.

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
17.10.2018	14:00 - 15:30	03.13.010	Federico Tombari	Introductory meeting
24.10.2018	14:00 - 15:30	03.13.010	Tim P. Abhishek	Object & Scene Reconstruction
31.10.2018	14:00 - 15:30	03.13.010	Shervin D. Hyunjun J.	6D Rigid Pose Estimation
07.11.2018	14:00 - 15:30	03.13.010	Abdul M. Haydar S.	Human Pose and ID
21.11.2018	14:00 - 15:30	03.13.010	Peter N. Rahul B.	Point Clouds
28.11.2018	14:00 - 15:30	03.13.010	Abinav V. Sumant D.	Navigation & Language
05.12.2018	14:00 - 15:30	03.13.010	Aashish T. Behiye A.	Image Completion
12.12.2018	14:00 - 15:30	03.13.010	Hooriya A. Giulia M.	SLAM & 3D Scene Understanding
09.01.2019	-	-	Back up	-