Seminar

The seminar of OBELIX team is currently held on thursdays 11:30 am, every two weeks, at the IRISA lab, Tohannic campus, room D106 (bat. ENSIBS). Usually, the presentation lasts 30 min and is followed by a discussion with the team.

The seminar is coordinated by Chloé Friguet.

Previous seminars

2019  2019-20 2020-21

Upcoming seminars (2020-2021)


  • Date: January, 25 (MONDAY)
  • Time: 14:00
  • Room : visio
  • Speaker: Florent Guiotte (LETG Rennes 2 and OBELIX, IRISA Vannes) – PhD Defense
  • Title: 2D/3D discretization of Lidar point clouds: Processing with morphological hierarchies and deep neural networks
  • Abstract: This thesis evaluates the relevance of morphological hierarchies and deep neural networks for analysing LiDAR data by means of several discretization strategies. The quantity of data increases  exponentially in coverage and resolution. However, actual datasets are not yet fully exploited due to the lack of  efficient methodological tools for this specific type of data. Morphological structures are known to extract  reliable multi-scale features while being extremely computationally efficient. In the mean time, the tremendous  breakthrough of deep learning in computer vision has shaken up the remote sensing community.  To this end we define and evaluate different discretization strategies of LiDAR data. In a first part, we reorganise the point clouds into 2D regular grids. We propose to derive several LiDAR features, trying to  extract complete elevation description and spectral values along with LiDAR specific information. In a second  part we re-organise the point clouds into 3D regular grids. The regular grids are sufficient to provide the  neighboring context needed for the morphological hierarchies, and the proposed grids are also adapted to the  input layers of state-of-the-art deep neural networks. The different methods are systematically validated in remote sensing scenarios.

  • Date: January, 28th
  • Time: 11:30
  • Room : visio
  • Speaker: Hoang-An Lê (Post-doc OBELIX, IRISA, Vannes)
  • Title: Novel View Synthesis from Single Images via Point Cloud Transformation
  • Abstract: In this paper the argument is made that for true novel view synthesis of objects, wherethe object can be synthesized from any viewpoint, an explicit 3D shape representation isdesired. Our method estimates point clouds to capture the geometry of the object, whichcan be freely rotated into the desired view and then projected into a new image. Thisimage, however, is sparse by nature and hence this coarse view is used as the input of animage completion network to obtain the dense target view. The point cloud is obtainedusing the predicted pixel-wise depth map, estimated from a single RGB input image,combined with the camera intrinsics. By using forward warping and backward warpingbetween the input view and the target view, the network can be trained end-to-end withoutsupervision on depth. The benefit of using point clouds as an explicit 3D shape for novelview synthesis is experimentally validated on the 3D ShapeNet benchmark. Source codeand data are available athttps://github.com/lhoangan/pc4novis
    Ref: BMVC’20 paper here

  • Date: February, 11th
  • Time: 11:30
  • Room :
  • Speaker:
  • Title:
  • Abstract:

  • Date: March, 11th
  • Time: 11:30
  • Room :
  • Speaker:
  • Title:
  • Abstract:

  • Date:  POSTPONED
  • Time: 11:30
  • Room :
  • Speaker:Yann Soulard (MCF LETG Rennes)
  • Title:
  • Abstract:

  • Date: POSTPONED
  • Time: 11:30
  • Room :
  • Speaker: Jeremy Cohen (CR PANAMA, IRISA Rennes)
  • Title: Learning with Low Rank Approximations
  • Abstract: Matrix and tensor factorizations are widespread techniques to extract structure out of data in a potentially blind manner. However, several issues may be raised: (i) these models have often been designed for blind scenarios whereas many applications now features extensive training databases, (ii) their output may not be interpretable because of the lack of identifiability of the parameters and (iii) computing a good solution can be difficult. In this talk, after describing the link between separable functions and tensor/matrix factorizations, we will show that separability and low rank approximations are actually already at the core of many machine learning problems such as dictionary learning or simultaneous factorizations.

Comments are closed.