The 3 years research project "GYROVIZ" addresses the challenge of automatic modeling of 3D physical scenes from located frames. The central motivation of our proposal stems from the observation of the current limitations of image-based modeling systems, which require a substantial amount of user interaction for matching the images. This limitation becomes even more critical when dealing with massive datasets to match.

While a considerable amount of efforts has previously been done to solve this issue purely from the algorithmic point of view, we propose to address it primarily from the technological side. Our solution hinges on a set of new accurate inertial sensors (specific fiber optic gyroscopes and accelerometers) which once coupled with an image acquisition device, provide a very precise measure of its physical location and pose.

Both robustness and efficiency of the image matching problem are this way substantially improved, as the solution space of the matching problem is drastically reduced, and the matching is always provided with good initial guesses

The algorithmic aspect of our proposal relies on state-of-the-art computer vision and geometric computing techniques for extracting and matching characteristic points and features from images, and for reconstructing 3D models with color attributes. Real-time reconstruction as well as feature and symmetry-preserving reconstruction are listed as topics for 2 Ph.D. theses (CEA/LIST and INRIA).

The complete system should be mobile and portable, and should allow a fully automatic 3D modeling of complex scenes. Two complementary laboratory models using the same localization unit will be developed in the framework of the project to make various sets of data acquisition for algorithm tests as well as to enable a practical evaluation of the potential of the technology with end-users:

  • A 3D real time video camera tracking system for virtual studio and postproduction purposes;
  • A 3D static scene and object modeling system for multimedia and engineering applications.

The project GYROVIZ is supported by the French Research Agency - ANR.

Key data

  • 3D scene reconstruction from pictures
  • Pictures and videos acquisitions
  • 3D tracking
  • 3D scene reconstruction in real time
  • Self-localization module able to provide 6 location information for each image
  • Geometric features reconstruction from point clouds

Consortium du projet GYROVIZ

GYROVIZ consortium has been led by SOFRESUD. It is composed by CEA research laboratory, INRIA and SUPMECA and the SME IXSEA.


  • Project coordination
  • Localized pictures acquisition system development and realization
  • Model integration and experimentation campaigns


GEOMETRICA is part of the INRIA Sophia-Antipolis research department. This team's goal is to develop a theoritical and experimental frame for effective geometrical calculations. The team, leader in the algorithmic geometric domain is one of the main actors, developing the algorithmic geometrics library, on CGAL (

  • High Resolution Reconstruction
  • Features (edges, corners, frontiers) extraction and dedicated scene characteristics
  • Geometrical objects reconstruction from points cloud, preserving metadata along the treatment chain.


The LIST is a key technology research center of 450 researchers, engineers and technicians working in three areas:

  • Embedded systems (architecture and design of systems, methods and facilities for software and system dependability, and intelligent vision systems);
  • Interactive systems (knowledge engineering, robotics, virtual reality and sensorial interfaces);
  • Signal detection and processing (ionizing radiation metrology and instrumentation, optical fiber sensors and non-destructive testing).

 Image & Vision Laboratory (15 members) of the CEA LIST involved in this project, develop applications around image processing and has a strong background in the 3D reconstruction of unknown environments considering visual sensors, computer vision and photogrammetry. Recent researches have lead to the simultaneous sparse reconstruction and localization of a camera moving in an unknown environment.


XSEA is a high tech SME with 180 people specialized in Fiber Optic gyroscope (IXSEA is one of the world leader in this field), acoustic sub sea positioning, acoustic sub sea imagery and magnetometer technologies. Its mission is to develop and deliver the most innovative products, systems and solutions to the market. These systems and solutions are developed and manufactured to the highest quality standards and in accordance with ISO 9001:2000 certification. IXSEA is a world-wide known expert in gyrometry and its Fiber Optic Gyroscope (FOG) technology is at the heart of versatile positioning and navigation systems.

The company is organized around 4 main industrial departments:

  • Inertial System Products Line (ISPL);
  • Imaging Systems and Acoustic Antennas (SIA2);
  • Acoustic Systems and Processing Software (SALT);
  • Development and Industrialization of new sensors (DINS).


SUPMECA (Institut Supérieur de Mécanique de Paris) is a State Institution of Higher Education and Research in Mechanical and Industrial Engineering.

The Institute proposes an engineering curriculum which combines a strong scientific background with industrial experience and leads to the national engineering degree.

Fundamental and applied industrial research is carried out by 70 people (including 30 University Professors and researchers and more than 20 Ph.D. students)


Contact Us

For more information Tel. : + 33 4 94 11 57 00

Haut de page