Address: EPFL-IC-CVLab, BC 368, Station 14, CH-1015 Lausanne (Switzerland)
E-mail: eduard dot trulls at epfl dot ch / Tel: +41 216 93 76 21
I am currently a post-doc at the Computer Vision Lab at EPFL in Lausanne, Switzerland, working on Deep Learning topics under the supervision of Prof. Pascal Fua. I obtained my PhD from the Institute of Robotics in Barcelona, Spain. My thesis explored novel strategies to enhance local, low-level features (e.g. SIFT, HOG) with global, mid-level data such as motion and segmentation cues, and was co-advised by Francesc Moreno and Alberto Sanfeliu. My work has been published in top computer vision conferences. Before my PhD I worked in mobile robotics.Links: GitHub / LinkedIn / Google Scholar / Videos
- September 2015: One paper accepted to ICCV (to appear).
- March 2015: Started my postdoc.
- February 2015: Successfully defended my PhD.
E. Simo-Serra(*), E. Trulls(*), L. Ferraz, I. Kokkinos and F. Moreno-Noguer
arXiv:1412.6537v2 (arxiv report, 2015)
We propose a novel framework for learning local image descriptors in a discriminative manner, with a siamese architecture of Deep Convolutional Neural Networks. We show how to mine the exponentially large number of corresponding/non-corresponding pairs, and demonstrate large improvements over the state of the art.
E. Trulls, S. Tsogkas, I. Kokkinos, A. Sanfeliu, F. Moreno-Noguer
Conference on Computer Vision and Pattern Recognition (CVPR), 2014
code: soon / poster / spotlight (video) / bibref
We combine bottom-up segmentation (SLIC superpixels) with DPMs. We use the superpixels to build soft segmentation masks at every scale and position. We use the masks to "clean up" the HOG features, splitting them into foreground and background channels.
E. Trulls, I. Kokkinos, A. Sanfeliu, F. Moreno-Noguer
Conference on Computer Vision and Pattern Recognition (CVPR), 2013
code / poster / spotlight (PDF) / bibref / site
We exploit segmentation data to construct appearance descriptors that can deal with occlusions and background motion. We use the segmentation to build soft segmentation masks, and downplay measurements likely to belong to a different region. We integrate this with SIFT and also with SID, a dense descriptor invariant by design to rotation and scaling.
E. Trulls, A. Sanfeliu, F. Moreno-Noguer
European Conference on Computer Vision (ECCV), 2012
poster / spotlight (video) / bibref / site
We use temporal consistency to match appearance descriptors and apply it to stereo on very ambiguous video sequences. Previous works define descriptors over spatiotemporal volumes, which is not applicable to wide-baseline scenarios—instead we extend 2D descriptors with optical flow estimates to capture the change around a feature point in time.
E. Trulls, A. Corominas Murtra, J. Pérez-Ibarz, G. Ferrer, D. Vasquez, Josep M. Mirats-Tur, A. Sanfeliu
Journal of Field Robotics, 2011
bibref / site
An extension of our 2010 IROS paper. We switch from 2D to 3D data for localization, and present experiments in a new urban area: a street open to the general public in the city of Barcelona, Spain.
A. Corominas Murtra, E. Trulls, J. M. Mirats Tur, A. Sanfeliu
International Conference on Simulation, Modelling, and Programming for Autonomous Robots (SIMPAR), 2010. Also in Simulation, Modelling, and Programming for Autonomous Robots, Lecture Notes in Computer Science, 2010.
This paper provides a detailed description of a set of algorithms to efficiently manipulate 3D models to compute physical constraints and range observation models, used for real-time robot localization.
A. Corominas Murtra, E. Trulls, O. Sandoval, J. Perez, D. Vasquez, J. M. Mirats Tur, M. Ferrer, A. Sanfeliu
International Conference on Intelligent Robots and Systems (IROS), 2010
We present a solution for fully autonomous navigation on urban, pedestrian environments, designed for highly mobile robots based on Segway platforms.
R. Valencia-Carreño, E. Teniente, E. Trulls, J. Andrade-Cetto
International Conference on Intelligent Robots and Systems (IROS), 2009
We present an approach to build 3D maps from 3D range data as the main input, based on the probabilistic alignment of the point clouds using SLAM.
J. Andrade-Cetto, A. Ortega, E. Teniente, E. Trulls, R. Valencia, A. Sanfeliu
Workshop on Network Robot Systems, International Conference on Intelligent Robots and Systems (IROS), 2009
An overview of the URUS project.
- Iasonas Kokkinos (CVC lab, Centrale-Supelec).
- Francesc Moreno (IRI, Barcelona, Spain).
- Edgar Simo (IRI, Barcelona, Spain).
For information, supplemental material and videos:
Some of the projects I have been part of: