Computer Vision and Machine Learning

In the Focus Group Computer Vision & Machine Learning, Carl von Linde Senior Fellow Prof. Daniel Cremers (TUM) works together with Rudolf Diesel Industry Fellow Prof. Michael Bronstein (Intel / Imperial College / University of Lugano).

The activities of the Computer Vision and Machine Learning focus group is primarily centered around the interplay between geometry, machine learning and computer vision. Analysis of geometric objects has been a topic of computer vision and pattern recognition since the inception of the field. Classical computer vision problems of “Shape-from-X” aim at recovering the geometric structure of a 3D object from multiple images (Shape from stereo) or different illumination conditions (photometric stereo). In the recent years, the interest in 3D data has increased dramatically, fuelled in part by the commercial availability of affordable and compact 3D sensors. Such sensors are nowadays found in a broad range of applications from drones and augmented reality to self-driving cars.

In July 2018, the Focus Group Computer Vision & Machine Learning organized the workshop Machine Learning for 3D Understanding.

Publications by the Focus Group

2019

  • 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…

2018

  • 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…
  • Gehre, Anne; Lim, Isaak; Kobbelt, Leif: Feature Curve Co-Completion in Noisy Data. Computer Graphics Forum 37 (2), 2018, 1-12 mehr…
  • 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…
  • 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…
  • 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…
  • 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…

2017

  • 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…