Looking for publications? All our latest publications are listed here, and you can also use our search functions to help find what you are looking for. Power users might also want to consider searching on the EPFL Infoscience site which provides advanced publication search capabilities.

Spinal cord repair: advances in biology and technology

Authors: Courtine, Grégoire, & Sofroniew, Michael V.

Individuals with spinal cord injury (SCI) can face decades with permanent disabilities. Advances in clinical management have decreased morbidity and improved outcomes, but no randomized clinical trial has demonstrated the efficacy of a repair strategy for improving recovery from SCI. Here, we summarize recent advances in biological and engineering strategies to augment neuroplasticity and/or functional recovery in animal models of SCI that are pushing toward clinical translation.


  • Published in: Nature Medicine (Volume: 25, Issue: 6)
  • DOI: 10.1038/s41591-019-0475-6
  • Read paper
  • Date: June 2019
Posted on: June 27, 2019
Posted on: June 19, 2019

Electrical spinal cord stimulation must preserve proprioception to enable locomotion in humans with spinal cord injury

  • Authors: Formento, Emanuele; Minassian, Karen; Wagner, Fabien; Mignardot, Jean-Baptiste; Le Goff-Mignardot, Camille Georgette Marie; Rowald, Andreas; Bloch, Jocelyne; Micera, Silvestro; Capogrosso, Marco; Courtine, Grégoire
Posted on: June 18, 2019

Reach-to-grasp motions: Towards a dynamic classification approach for upper-limp prosthesis

  • Authors: Batzianoulis, Iason; Simon, Annie; Hargrove, Levi; Billard, Aude
Posted on: June 18, 2019

Event-based Vision: A Survey

  • Authors: Gallego, Guillermo; Delbruck, Tobi; Orchard, Garrick; Bartolozzi, Chiara; Taba, Brian; Censi, Andrea; Leutenegger, Stefan; Davison, Andrew; Conradt, Joerg; Daniilidis, Kostas; Scaramuzza, Davide
Posted on: June 7, 2019

Unsupervised Moving Object Detection viaContextual Information Separation

Authors: Yang, Yanchao; Loquercio, Antonio; Scaramuzza, Davide; Soatto, Stefano


We propose an adversarial contextual model for detecting moving objects in images. A deep neural network istrained to predict the optical flow in a region using information from everywhere else but that region (context), while another network attempts to make such context as uninformative as possible. The result is a model where hypotheses naturally compete with no need for explicit regularization or hyper-parameter tuning. Although our method requires no supervision whatsoever, it outperforms several methods that are pre-trained on large annotated datasets. Our model can be thought of as a generalization of classical variational generative region-based segmentation, but in a way that avoids explicit regularization or solution of partial differential equations at run-time. We publicly release all our code and trained networks


  • Presented at: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, USA, 2019
  • Read paper
  • Data set
  • Date: 2019
Posted on: May 31, 2019