Sergey Zakharov

Contact Email: sergey.zakharov[at]tum.de Address: 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

Research Interests Scalable 3D Object Detection Object Classification and Pose Estimation Metric Learning Domain Adaptation Augmented Reality

Education

• 2016: Master of Science - Biomedical Computing at Technical University Munich, Chair for Computer Aided Medical Procedures (CAMP)
  Thesis: 3D Object Instance Recognition and Pose Estimation in Cluttered Scenes Using CNNs


• 2015: Master of Science - Computational Science and Engineering at Technical University Munich, Chair for Scientific Computing
  Thesis: Hybrid Lattice Boltzmann-Molecular Dynamics Simulations Using the Palabos and OpenLB^? Frameworks


• 2012: Bachelor of Science - Mechanical Engineering and Production Technology at Saimaa UAS and FH Schmalkalden
  Thesis: Planning, Design and Realization of a 500000V Van-de-Graaff Generator

List of Publications

2020
	R. Kaskman, I. Shugurov, S. Zakharov, S. Ilic 6DoF Pose Estimation of Textureless Objects from Multiple RGB Frames European Conference on Computer Vision Workshops (ECCVW), Online, August 2020. (bib)
	S. Zakharov, W. Kehl, A. Bhargava, A. Gaidon Autolabeling 3D Objects with Differentiable Rendering of SDF Shape Priors IEEE Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, June 2020 [oral]. The first two authors contributed equally to this work. (bib)
2019
	B. Planche, S. Zakharov, Z. Wu, A. Hutter, H. Kosch, S. Ilic Seeing Beyond Appearance - Mapping Real Images into Geometrical Domains for Unsupervised CAD-based Recognition International Conference on Intelligent Robots and Systems (IROS), Macau, China, November 2019. The first two authors contributed equally to this work. (bib)
	S. Zakharov, W. Kehl, S. Ilic DeceptionNet: Network-Driven Domain Randomization International Conference on Computer Vision (ICCV), Seoul, Korea, October 2019. (bib)
	S. Zakharov, I. Shugurov, S. Ilic DPOD: 6D Pose Object Detector and Refiner International Conference on Computer Vision (ICCV), Seoul, Korea, October 2019. The first two authors contributed equally to this work. (bib)
	R. Kaskman, S. Zakharov, I. Shugurov, S. Ilic HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objects International Conference on Computer Vision Workshops (ICCVW), Seoul, Korea, October 2019. (bib)
2018
	S. Zakharov, B. Planche, Z. Wu, A. Hutter, H. Kosch, S. Ilic Keep it Unreal: Bridging the Realism Gap for 2.5 D Recognition with Geometry Priors Only International Conference on 3DVision (3DV), Verona, Italy, September 2018 [oral]. The first two authors contributed equally to this work. (bib)
	M. Bui, S. Zakharov, S. Albarqouni, S. Ilic, N. Navab When Regression meets Manifold Learning for Object Recognition and Pose Estimation Proceedings of IEEE International Conference on Robotics and Automation (ICRA), 21-25 May, 2018, Brisbane, Australia (bib)
2017
	B. Planche, Z. Wu, K. Ma, S. Sun, S. Kluckner, T. Chen, A. Hutter, S. Zakharov, H. Kosch, J. Ernst DepthSynth: Real-Time Realistic Synthetic Data Generation from CAD Models for 2.5D Recognition International Conference on 3D Vision (3DV), Qingdao, China, October 2017 (bib)
	S. Zakharov, W. Kehl, B. Planche, A. Hutter, S. Ilic 3D Object Instance Recognition and Pose Estimation Using Triplet Loss with Dynamic Margin International Conference on Intelligent Robots and Systems (IROS), Vancouver, Canada, September 2017 (bib)

Teaching Assistance

• Lecture Tracking and Detection in Computer Vision (2018WiSe)
• Lecture Tracking and Detection in Computer Vision (2017WiSe)