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

Prof. Nassir Navab, Federico Tombari, Christian Rupprecht, Felix Achilles, Wadim Kehl, Benjamin Busam

Type: Advanced Seminar Course Module IN8901
Type: Master Seminar Module IN2107
Type: Seminar Module IN0014
SWS: 2+0
ECTS: 4 Credits
Location: Seminar room 03.13.010
Time: 15:00 - 17:00
Course Language: English

Announcements

• Next session (12.11.2015) will be held in 01.13.010
• The slides of the introductory meeting can be found here.
• An introductory meeting was held on July 9th 2015, 1:30pm in 03.13.010

Introduction

• The Seminar Course concerns recent advances in the field of 3D Computer Vision. The Seminar will propose a list of recent scientific articles related to the main current research topics of 3D Computer Vision, such as 3D keypoint detection, 3D features, point cloud registration, 3D object recognition and classification, SLAM and stereo vision.

Registration

• The registration is over
• It was performed though 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.zip.
• 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

The list of papers:

Authors	Title	Conference/Journal	Tutor	Student
Zollhöfer, Michael, et al.	Real-time Non-rigid Reconstruction using an RGB-D Camera	SIGGRAPH 2014	Mira	Hasnain Rehman Gondal
Dou, M., Taylor, J., Fuchs, H., Fitzgibbon, A., & Izadi, S.	3D Scanning Deformable Objects with a Single RGBD Sensor	CVPR 2015	Mira	Michael Gutbrod
Newcombe, R. A., Fox, D., & Seitz, S. M.	DynamicFusion: Reconstruction and Tracking of Non-rigid Scenes in Real-Time	CVPR 2015	Mira	Arslan Ali Syed
David Eigen, Rob Fergus	Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture	arXiv 2014	Benjamin	Christoph Baur
Jure Zbontar, Yann LeCun	Computing the Stereo Matching Cost with a Convolutional Neural Network	CVPR 2015	Benjamin	Markus Herb
Paul Wohlhart and Vincent Lepetit	Learning Descriptors for Object Recognition and 3D Pose Estimation	CVPR 2015	Wadim	Sara Hajmohammadalitorkabadi
Saurabh Gupta, Ross Girshick, Pablo Arbelaez, and Jitendra Malik	Learning Rich Features from RGB-D Images for Object Detection and Segmentation	ECCV 2014	Wadim	Johannes Rausch
C. Qian, X. Sun, Y. Wei, X. Tang, J. Sun	Realtime and Robust Hand Tracking from Depth	CVPR 2014	Paul	Matthias Grimm
Z. Wu, S. Song, A. Khosla, F. Yu, L. Zhang, X. Tang and J. Xiao	3D ShapeNets: A Deep Representation for Volumetric Shape Modeling	CVPR 2015	Christian	Mahdi Saleh
R. Socher, B. Huval, B. Bhat, C.D. Manning, A.Y. Ng	Convolutional-Recursive Deep Learning for 3D Object Classification	NIPS 2012	Leslie	Leonhard Rauh
Ho Yub Jung, Soochahn Lee, Yong Seok Heo, Il Dong Yun	Random Tree Walk toward Instantaneous 3D Human Pose Estimation	CVPR 2015	Paul	Dominik Gutermuth
Li, Sijin, and Antoni B. Chan	3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network	ACCV 2014	Christian	Andreas Meißner
J. Valentin, V. Vineet, M.-M. Cheng, D. Kim, J. Shotton, P. Kohli, M. Niessner, A. Criminisi, S. Izadi, P. Torr	SemanticPaint: Interactive 3D Labeling and Learning at your Fingertips	SIGGRAPH 2015	Keisuke	Adam Kosiorek
J.Shotton, B.Glocker, C.Zach, S.Izadi, A.Criminisi, A.Fitzgibbon	Scene coordinate regression forests for camera relocalization in RGB-D images	CVPR 2013	David	Sergey Zakharov
T.-J. Chin, P. Purkait, A. Eriksson, D. Suter	Efficient Globally Optimal Consensus Maximisation with Tree Search	CVPR 2015	Tolga	Homa Rasouli

Schedule

This is the final schedule for the course. Each registered student is required to attend all presentations. All lectures take place in Seminarraum 03.13.010.

Date	Time	Topic	Speaker	Material
October 29th	15:00	Random Tree Walk toward Instantaneous 3D Human Pose Estimation	Dominik Gutermuth
October 29th	15:30	3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network	Andreas Meißner
October 29th	16:00	Convolutional-Recursive Deep Learning for 3D Object Classification	Leonhard Rauh
November 12th	15:00	3D Scanning Deformable Objects with a Single RGBD Sensor	Michael Gutbrod
November 12th	15:30	3D ShapeNets: A Deep Representation for Volumetric Shape Modeling	Mahdi Saleh
November 12th	16:00	Computing the Stereo Matching Cost with a Convolutional Neural Network	Markus Herb	Report Presentation
November 19th	15:00	Learning Descriptors for Object Recognition and 3D Pose Estimation	Sara Hajmohammadalitorkabadi
November 19th	15:30	DynamicFusion: Reconstruction and Tracking of Non-rigid Scenes in Real-Time	Arslan Ali Syed
November 19th	16:00	Learning Rich Features from RGB-D Images for Object Detection and Segmentation	Johannes Rausch
December 3rd	15:00	Real-time Non-rigid Reconstruction using an RGB-D Camera	Hasnain Rehman Gondal
December 3rd	15:30	Efficient Globally Optimal Consensus Maximisation with Tree Search	Homa Rasouli
December 3rd	16:00	Scene coordinate regression forests for camera relocalization in RGB-D images	Sergey Zakharov
December 10th	15:00	Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture	Christoph Baur	Report Presentation
December 10th	15:30	Realtime and Robust Hand Tracking from Depth	Matthias Grimm
December 10th	16:00	SemanticPaint: Interactive 3D Labeling and Learning at your Fingertips	Adam Kosiorek