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

PD Federico Tombari, Nikolas Brasch, Evin Pinar Ornek, HyunJun Jung

Course number: Module IN4826
Type: Advanced Seminar Course Module IN8901, Master Seminar Module IN2107, 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, 13:00 - 13:30, slides
• All sessions will be held over Zoom

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. 3000 words is written and submitted as a markdown 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
1	Nie et. al.	RfD?-Net: Point Scene Understanding by Semantic Instance Reconstruction	CVPR 2021	paper	Yida Wang	Daoyi
2	Chibane et al.	Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion	CVPR 2020	paper	Yida Wang	Hanzhi
3	Zhao et. al.	Point Transformer	arxiv	paper	Evin Pinar Ornek	Ömer
4	Wiles et al.	SynSin?: End-to-end View Synthesis from a Single Image	CVPR 2020	paper	Evin Pinar Ornek	Tom
5	Yu et al.	pixelNeRF: Neural Radiance Fields from One or Few Images	CVPR 2021	paper	Shun-Cheng Wu	Jonathan
6	Sucar et al.	iMAP: Implicit Mapping and Positioning in Real-Time	CVPR 2021	paper	Shun-Cheng Wu	Anja
7	J.Yang et al.	Cost Volume Pyramid Based Depth Inference for Multi-View Stereo	CVPR 2020	paper	HyunJun Jung	Zhuolun
8	X.Long et al.	Multi-view Depth Estimation using Epipolar Spatio-Temporal Networks	CVPR 2021	paper	HyunJun Jung	Felix
9	Germain et al.	Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation	CVPR 2021	paper	Mahdi Saleh	Aditya
10	Wang et al.	GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation	CVPR 2021	paper	Yan Di?	Nijat
11	Li et al.	Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes	CVPR 2020	paper	Pengyuan Wang	Christian
12	Mei et al.	Don't Hit Me! Glass Detection in Real-world Scenes	CVPR 2020	paper	Yanyan Li	Ihsan

Schedule

Each student is required to attend all presentations.

Date	Time	Place	Speaker	Topic
Mon, Februar 1, 2021	13:00-13:30	Zoom	Tutors	Introductory talk slides
Fri, April 16, 2021	15:00-17:00	Zoom	Federico Tombari	Introductory session slides
Fri, April 30, 2021	15:00-17:00	Zoom	Daoyi, Hanzhi, Ömer	Student presentations
Fri, May 21, 2021	15:00-17:00	Zoom	Tom, Jonathan, Anja	Student presentations
Fri, June 11, 2021	15:00-17:00	Zoom	Zhuolun, Felix, Aditya	Student presentations
Fri, July 2, 2021	15:00-17:00	Zoom	Nijat, Christian, Ihsan	Student presentations
Fri, July 16, 2021	15:00-17:00	Zoom		Backup