Haowen Deng (邓皓文)

M.Sc. Haowen Deng Technische Universität München Siemens AG Email: haowen.deng@tum.de Adress: Technische Universität München Fakultät für Informatik Boltzmannstr. 3 85748, Garching b. München Deutschland Siemens AG Research & Technology Center Otto-Hahn-Ring 6 81739, München Deutschland

Brief Resume

I am currently a Ph.D candidate at Chair for Computer Aided Medical Procedures & Augmented Reality (CAMP), Fakultät für Informatik in Technische Universität München and Siemens AG. My supervisor is Slobodan Ilic. My Phd topic is related with Computer Vision and Machine Learning. I am interested in using Machine Learning methods, especially Deep Learning, to affiliate better understanding of 3D Geometries and to solve related vision tasks.

Research Interests

• Machine Learning
• Computer Vision
• Deep Learning
• 3D Geometry Understanding
• Feature Learning
• Matching & Registration
• Simultaneous Localization and Mapping (SLAM)
• Semantic Segmentation
• Object Detection & Tracking

Education

• 2017 - now, Computer Science, Technical University of Munich, Germany, Phd Candidate
• 2014 - 2016, Computer Science and Technology, National University of Defense Technology, China, Master
• 2010 - 2014, Network Engineering, National University of Defense Technology, China, Bachelor

Teaching Assistance

• Lecture: Tracking and Detection in Computer Vision (WS 17/18)
• Lecture: Tracking and Detection in Computer Vision (WS 16/17)

Publications

2020
	M. Bui, T. Birdal, H. Deng, S. Albarqouni, L. Guibas, S. Ilic, N. Navab 6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference Proceedings of European Conference on Computer Vision, 2020, Glasgow (bib)
2019
	Y. Zhao, T. Birdal, H. Deng, F. Tombari 3D Point-Capsule Networks IEEE Computer Vision and Pattern Recognition (CVPR), Long Beach, United States, June 2019 (bib)
	H. Deng, T. Birdal, S. Ilic 3D Local Features for Direct Pairwise Registration IEEE Computer Vision and Pattern Recognition (CVPR), Long Beach, United States, June 2019 (bib)
2018
	H. Deng, T. Birdal, S. Ilic PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors European Conference On Computer Vision (ECCV), Munich, Germany, September 2018 (bib)
	H. Deng, T. Birdal, S. Ilic PPFNet: Global Context Aware Local Features for Robust 3D Point Matching IEEE Computer Vision and Pattern Recognition (CVPR), Salt Lake City, United States, June 2018 [spotlight] (bib)