Members
Overall Objectives
Research Program
Highlights of the Year
New Software and Platforms
New Results
Bilateral Contracts and Grants with Industry
Partnerships and Cooperations
Dissemination
Bibliography
XML PDF e-pub
PDF e-Pub


Section: Partnerships and Cooperations

National Initiatives

ANR

ANR DRAO

Participant : Adrien Bousseau.

https://www-sop.inria.fr/members/Adrien.Bousseau/drao/

The ANR DRAO is a young researcher project coordinated by Adrien Bousseau, in collaboration with the InSitu project team at Inria Saclay - Ile de France (W. Mackay and T. Tsandilas) and the MANAO project team (P. Barla and G. Guennebaud) and POTIOC project team (M. Hachet) at Inria Bordeaux - Sud Ouest. The goal of this collaboration is to develop novel drawing tools for amateurs as well as for expert designers and illustrators, combining expertise in Computer Graphics (REVES and MANAO) and Human-Computer Interaction (InSitu, POTIOC). This ANR project funds the PhD of Emmanuel Iarussi.

While the ANR DRAO ended in 2015, it has resulted in a publication at ACM Conference on Human Factors in Computing Systems (CHI) 2016 [9]. Adrien Bousseau received an ANR Young Researcher Award for coordinating this project.

ANR SEMAPOLIS

Participants : George Drettakis, Abdelaziz Djelouah, Theo Thonat.

This ANR project started in October 2013. The goal is to use semantic information to improve urban reconstruction and rendering. The consortium is led by ENPC (R. Marlet) and includes the Inria Willow team and the GREY-C laboratory on image processing. Our contribution will be in the rendering of urban models, in particular using image-based rendering algorithms.

This year, the ANR SEMAPOLIS resulted in five publications on multi-view segmentation [10], multi-view inpainting [13], image-based rendering of cars [12] and interiors [6], and procedural modeling of buildings [8]. Two of these projects rely on a deep learning method from the ENPC group to identify semantic object categories in images (e.g., cars, people etc.) [13], [12]. In [12] we also collaborated with the ENPC group to use a deep learning method to allow the use of rendered images to identify objects in photographs. These collaborations have been extremely fruitful for our group, and have opened the way to several new collaborations with ENPC.