Section: Bilateral Contracts and Grants with Industry

Bilateral Contracts with Industry

Google X

Participants : Cédric Portaneri, Pierre Alliez.

We developed a novel approach and software prototype for the compression of 3D models. Our main focus is on progressive compression of surface triangle meshes with color textures, with emphasis on fine grain, genericity and flexible metric. The proposed methodology is to turn the input models into a stream of refinements, in which both mesh and texture refinement details are multiplexed in accordance to rate-distortion principles. Fine grain control is achieved through considering all components, local as well as non-local, from both the mesh and its textures: mesh complexity, vertex accuracy, texture definition and accuracy. We leveraged the recent advances on perceptual metrics to improve the visual appearance, and performed joint consolidation and encoding of the models to further optimize the rate-distortion tradeoffs and visual perception.

Dorea technology

Participants : Vincent Vadez, Pierre Alliez.

In collaboration with SME Dorea Technology, our objective is to advance the knowledge on the radiative thermal simulation of satellites, via geometric model reduction. The survival of a satellite is related to the temperature of its components, the variation of which must be controlled within safety intervals. In this context, the thermal simulation of the satellite for its design is crucial to anticipate the reality of its operation. This CIFRE project started in August 2018, for a total duration of 3 years.

Luxcarta

Participants : Jean-Philippe Bauchet, Florent Lafarge.

The goal of this collaboration is to design automated approaches for producing city models from the last generation of satellites. In particular, this project investigates geometric representations for images and 3D data that are more compact and meaningful than traditional pixel and voxel grids, the intuition being to synthesize massive satellite data to reconstruct objects in 3D in a more scalable manner than existing methods. This CIFRE project started in October 2016, for a total duration of 3 years.

CNES and Acri-ST

Participants : Onur Tasar, Yuliya Tarabalka, Pierre Alliez.

The aim is to devise efficient representations for satellite images. The project started in October 2017, for a total duration of 3 years.

CSTB

Participants : Hao Fang, Mulin Yu, Florent Lafarge.

This collaboration takes the form of two independent contracts. The first project investigated the automatic conversion of raw 3D data to polyhedral surfaces that approximate man-made objects at some key structural representation scales. This project started in March 2016, for a total duration of 3 years. The second project investigates the design of as-automatic-as-possible algorithms for repairing and converting Building Information Modeling (BIM) models of buildings in different urban-specific CAD formats using combinatorial maps. This project started November 2019, for a total duration of 3 years.

IRT Saint-Exupéry

Participants : Gaetan Bahl, Florent Lafarge.

This project investigates low-power deep learning architectures for detecting, localizing and characterizing changes in temporal satellite images. These architectures are designed to be exploited on-board satellites with low computational resources. The project started in March 2019, for a total duration of 3 years.

Dassault Systèmes

Participants : Julien Vuillamy, Pierre Alliez, Florent Lafarge.

This project investigates algorithms for reconstructing city models from multi-sourced data. 3D objects are reconstructed by filtering, parsing and assembling planar shapes. The project started in April 2018, for a total duration of 3 years.