Michael Bronstein

Rudolf Diesel Industry Fellow

Imperial College/ University of Lugano/ Intel/ Twitter

Computational Science

Daniel Cremers

Focus Group
Computer Vision and Machine Learning

Short CV

Michael Bronstein is a professor at USI Lugano, Switzerland and Imperial College London, UK where he holds the Chair in Machine Learning and Pattern Recognition. He is also a principal engineer at Intel Perceptual Computing. Michael got his Ph.D. with distinction in Computer Science from the Technion in 2007. He is a Fellow of IAPR, Senior Member of the IEEE, alumnus of the Technion Excellence Program and the Academy of Achievement, ACM Distinguished Speaker, and a member of the Young Academy of Europe. His research appeared in the international media such as CNN and was recognized by numerous prestigious awards, including several best paper awards, four ERC grants (Starting Grant 2012, Proof of Concept Grants 2016 and 2018, and Consolidator Grant 2016), two Google Faculty Research Award (2015, 2017), a Radcliffe Fellowship from the Institute for Advanced Study at Harvard University (2017), and Rudolf Diesel Industrial Fellowship from TU Munich (2017), the Amazon AWS Machine Learning Research Award (2018), a Dalle Molle Prize (2018), and a Royal Society Wolfson Merit Award (2018). In 2014, he was invited as a Young Scientist to the World Economic Forum, an honor bestowed on forty world's leading scientists under the age of forty. He was a guest speaker at the World Economic Forum meeting in Dalian, China in 2015. Michael is the author of the first book on deformable 3D shape analysis, editor of four books, over 100 papers in top scientific journals and conferences, and inventor of over 30 granted patents. He has chaired over a dozen of conferences and workshops in his field, and has served as area chair at ECCV 2016 and ICCV 2017 and as associate editor of IJCV, CVIU, and SIAM Imaging Sciences journals. In addition to academic work, Michael is an inventor and serial entrepreneur. He was a co-founder and technology executive at Novafora (2005-2009) developing large-scale video analysis methods, and one of the chief technologists at Invision (2009-2012) developing low-cost 3D sensors. Following the multi-million acquisition of Invision by Intel in 2012, Michael has been one of the key developers of the Intel RealSense technology. His most recent venture is Fabula AI, a startup dedicated to algorithmic detection of fake news. Just a year after incorporation it was aquired by Twitter in June 2019. Following the deal Michael joined Twitter as Head of Graph Learning Research.

Selected Awards

2018 Dalle Molle Prize

2018 Royal Society Wolfson Research Merit Award

2018 ERC Proof of Concept Grant

2018 Amazon AWS Machine Learning Research Award

2018 Fellow, International Association for Pattern Recognition (IAPR)

2017 Google Faculty Research Award

2017 Radcliffe fellowship, Harvard University

2017 Rudolf Diesel industrial fellowship, TU Munich

2016 ERC Consolidator Grant 2016 ERC Proof of Concept Grant

2016 Best Paper Award, Symposium on Geometry Processing

2016 Google Faculty Research Award

2015 Intel High Five Award

2015 ACM Distinguished Speaker

2015 Elected member, Global Young Academy

2015 Elected member, Young Academy of Europe

2014 World Economic Forum Young Scientist

2012 EUROGRAPHICS Service Award

2012 ERC Starting Grant

2005 Adams Fellowship

2005 Best Paper Award, Copper Mountain Conference on Multigrid Methods

2003 Hershel Rich Technion Innovation Award

2003 Gensler Prize

2003 Honorary Student Delegate, International Achievement Summit

2002 Alumnus, Technion Excellence Program

2002 Kasher Prize for best undergraduate project

2002 Thomas Schwartz Award for best undergraduate project

2001 Technion Humanities and Arts Department prize

Research Interests

• Theoretical and computational methods in spectral and metric geometry and their application to problems in computer vision, pattern recognition, shape analysis, computer graphics, image processing, and machine learning

• Deep learning on non-Euclidean structured data (graphs and manifolds)

Selected Publications

  • F. Monti, D. Boscaini, J. Masci, E. Rodolà, M. M. Bronstein: Geometric deep learning on graphs and manifolds using mixture model CNNs. Proc. Computer Vision and Pattern Recognition (CVPR), 2017.
  • Litany, O.; Rodolà, E.; Bronstein, A. M.; Bronstein, M. M.; Cremers, D.: Non-Rigid Puzzles. Computer Graphics Forum 35 (5), 2016, 135-143.
  • Boscaini, D.; Masci, J.; Rodolà, E.; Bronstein, M. M.; Cremers, D.: Anisotropic Diffusion Descriptors. Computer Graphics Forum 35 (2), 2016, 431-441.
  • Rodolà, E.; Cosmo, L.; Bronstein, M. M.; Torsello, A.; Cremers, D.: Partial Functional Correspondence. Computer Graphics Forum 36 (1), 2016, 222-236.
  • D. Boscaini, J. Masci, E. Rodolà, M. M. Bronstein: Learning shape correspondence with anisotropic convolutional neural networks. Proc. Neural Information Processing Systems (NIPS), 2016.
  • A. Kovnatsky, K. Glashoff, M. M. Bronstein: MADMM: a generic algorithm for non-smooth optimization on manifolds. Proc. European Conf. Computer Vision (ECCV), 2016.
  • Boscaini, Davide; Eynard, Davide; Kourounis, Drosos; Bronstein, Michael M.: Shape-from-Operator: Recovering Shapes from Intrinsic Operators. Computer Graphics Forum 34 (2), 2015, 265-274.
  • D. Eynard, A. Kovnatsky, M. M. Bronstein, K. Glashoff, A. M. Bronstein: Multimodal manifold analysis using simultaneous diagonalization of Laplacians. IEEE Trans. Pattern Analysis and Machine Intelligence (PAMI), 2015, 2505-2517.
  • D. Boscaini, J. Masci, S. Melzi, M. M. Bronstein, U. Castellani, P. Vandergheynst: Learning class-specific descriptors for deformable shapes using localized spectral convolutional networks. Computer Graphics Forum, 2015, 13-23.
  • J. Masci, D. Boscaini, M. M. Bronstein, P. Vandergheynst: Geodesic convolutional neural networks on Riemannian manifolds. Proc. Workshop on 3D Representation and Recognition (3dRR), 2015.

Publications as TUM-IAS-Fellow


  • Rodolà, E.; Lähner, Z.; Bronstein, A. M.; Bronstein, M. M.; Solomon, J.: Functional Maps Representation On Product Manifolds. Computer Graphics Forum 38 (1), 2019, 678-689 mehr… BibTeX Volltext ( DOI )


  • Choma, Nicholas; Monti, Federico; Gerhardt, Lisa; Palczewski, Tomasz; Ronaghi, Zahra; Prabhat, Prabhat; Bhimji, Wahid; Bronstein, Michael; Klein, Spencer; Bruna, Joan: Graph Neural Networks for IceCube Signal Classification. 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), IEEE, 2018 mehr… BibTeX Volltext ( DOI )
  • Gehre, Anne; Lim, Isaak; Kobbelt, Leif: Feature Curve Co-Completion in Noisy Data. Computer Graphics Forum 37 (2), 2018, 1-12 mehr… BibTeX Volltext ( DOI )
  • Jan Svoboda, Jonathan Masci, Federico Monti, Michael M. Bronstein, Leonidas Guibas: PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks. Proceedings of the International Conference on Learning Representations, 2018 mehr… BibTeX
  • Litany, Or; Bronstein, Alex; Bronstein, Michael; Makadia, Ameesh: Deformable Shape Completion with Graph Convolutional Autoencoders. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, 2018 mehr… BibTeX Volltext ( DOI )
  • Monti, Federico; Otness, Karl; Bronstein, Michael M.: MOTIFNET: A MOTIF-BASED GRAPH CONVOLUTIONAL NETWORK FOR DIRECTED GRAPHS. 2018 IEEE Data Science Workshop (DSW), IEEE, 2018 mehr… BibTeX Volltext ( DOI )
  • Nogneng, D.; Melzi, S.; Rodolà, E.; Castellani, U.; Bronstein, M.; Ovsjanikov, M.: Improved Functional Mappings via Product Preservation. Computer Graphics Forum 37 (2), 2018, 179-190 mehr… BibTeX Volltext ( DOI )


  • F. Monti, D. Boscaini, J. Masci, E. Rodolà, M. M. Bronstein: Geometric deep learning on graphs and manifolds using mixture model CNNs. Proc. Computer Vision and Pattern Recognition (CVPR), 2017 mehr… BibTeX
  • Melzi, S.; Rodolà, E.; Castellani, U.; Bronstein, M. M.: Localized Manifold Harmonics for Spectral Shape Analysis. Computer Graphics Forum 37 (6), 2017, 20-34 mehr… BibTeX Volltext ( DOI )