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

PD Federico Tombari, Fabian Manhardt, Johanna Wald

Course number: Module IN4826
Type: Advanced Seminar Course Module IN8901, Master Seminar Module IN2107, Seminar Module IN0014
SWS: 2+0
ECTS: 5 Credits
Location: CAMP Seminar Room, 00.08.055
Time: Wednesday, 10.00am-noon
Course Language: English

Announcements

• You can submit your motivation letter via email to fabian.manhardt@tum.de or johanna.wald@tum.de
• Preliminary Meeting: July 19th, 4pm, in room: CAMP Seminar Room, 03.13.010
  The slides can be found here

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.
• Blog Post: A blog post of approx. 5000 words is written and submitted (either as a zip file or via a git repository) as a markdown html file two weeks after the presentation.
• 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 blog post and presentation have to be done in English.

List of Topics and Material

Authors	Title	Conference	Link	Tutor	Student
Wang et al.	Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation	CVPR 2019	paper	Mahdi Saleh	Vladimir
Kanazawa et al.	Learning 3D Human Dynamics from Video	CVPR 2019	paper	Manuel Nickel	Lukas
Peng et al.	SFV: Reinforcement Learning of Physical Skills from Videos	SIGGRAPH ASIA 2018	paper	Manuel Nickel	Chantal Marie
Kato et al.	Neural 3D Mesh Renderer	CVPR 2018	paper	Fabian Manhardt	Anna
Kanazawa et al.	Learning Category-Specific Mesh Reconstruction from Image Collections	ECCV 2018	paper	Fabian Manhardt	Mert
Yao et al.	3D-Aware Scene Manipulation via Inverse Graphics	NeurIPS? 2018	paper	Helisa Dhamo	Sina
Schops et al.	BAD SLAM: Bundle Adjusted Direct RGB-D SLAM	CVPR 2019	paper	Nikolas Brasch	Lex
Geneva et al.	An Efficient Schmidt-EKF for 3D visual-inertial SLAM	CVPR 2019	paper	Nikolas Brasch	Zechen
Graham et al.	3D Semantic Segmentation with Submanifold Sparse Convolutional Networks	CVPR 2018	paper	Johanna Wald	Aleksandr
Liu et al.	FlowNet3D?: Learning Scene Flow in 3D Point Clouds	CVPR 2019	paper	Mahdi Saleh	Stefan
Shi et al.	PointRCNN?: 3D Object Proposal Generation and Detection from Point Cloud	CVPR 2019	paper	Johanna Wald	Madhan
Park et al.	DeepSDF?: Learning Continuous Signed Distance Functions for Shape Representation	CVPR 2019	paper	Shun-Cheng Wu	Can
Xu et al.	DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction	CVPR 2019	paper	Shun-Cheng Wu	Philipp
Li at al.	RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion	CVPR 2019	paper	Yida Wang	Alexander

Schedule

Each student is required to attend all presentations.

Date	Time	Place	Speaker	Topic
Fri, October 18, 2019	16:00-18:00	3.13.010, Seminarraum	Federico Tombari	Introductory talk slides
Wed, November 6, 2019	10:00-12:00	3.13.010, Seminarraum	Vladimir, Lukas, Chantal	Pose Estimation (6D Object / Human)
Wed, November 27, 2019	10:00-12:00	00.08.055, Seminarraum	Anna, Mert, Sina	Neural 3D Rendering
Wed, December 4, 2019	10:00-12:00	00.08.055, Seminarraum	Lex, Zechen	SLAM
Wed, December 11, 2019	10:00-12:00	00.08.055, Seminarraum	Aleksandr, Stefan, Madhan	3D Scene Understanding
Wed, December 18, 2019	10:00-12:00	00.08.055, Seminarraum	Can, Philipp, Alexander	Object & Scene Reconstruction / Completion
Wed, January 8, 2020	10:00-12:00	00.08.055, Seminarraum		Backup
Wed, January 15, 2020	10:00-12:00	00.08.055, Seminarraum		Backup