Welcome to the PRoVisG Mars 3D Challenge!
The Mars 3D Challenge aims at testing and improving the state of the art in visual odometry and 3D terrain reconstruction in planetary exploration.
The task of the challenge is to reconstruct depth, camera trajectory and 3D map of Mars landscape observed by the Mars Exploration Rovers (MER). Results of the challenge will help to develop technology for future planetary mission such as ESA ExoMars.
The challenge consists of three stages. The results of the challenge were evaluated by a the PRoVisG Project consortium including the JPL NASA operating the MERs. Results of the challenge are presented at a ICCV 2011 workshop “CVVT:E2M – Computer Vision in Vehicle Technology: From Earth to Mars” and published in a follow-up journal paper.
The winners of this challenge are members of the IMAGINE Group. IMAGINE is a joint project of the École des Ponts ParisTech (ENPC) and the French Scientific and Technical Centre for Building (CSTB). IMAGINE is now part of the Center for Visual Computing (CVC), in association with the École Centrale de Paris (ECP), and it is part as well of the Computer Science lab (LIGM) of University Paris Est (UPE). Some participants to the challenge are also partly supported by Mikros Image.
IMAGINE has been working for several years on dense multi-view stereovision. The main focus of the group has been on high precision 3D surface reconstruction from images, targeting large-scale data sets taken under uncontrolled conditions.
IMAGINE currently hold the best results worldwide on the Strecha et al. reference benchmark, with the most complete and the most precise reconstructions. One of the key and original components of the IMAGINE pipeline is a variational mesh refinement that reprojects mesh hypotheses into the original images to improve photo consistency. This expertise and software has been recently transferred to the startup company Acute3D, powering Autodesk‘s 123D Catch (formerly project Photofly), a web service to create 3D models from photographs.
IMAGINE is currently working on improving calibration using statistical methods, e.g., in the framework of the Callisto project, also in association with the CNES in the context of the MISS project. IMAGINE is interested in other sensors too, such as lasers and Kinect, as well semantization, e.g., for high-level building model reconstruction.
For more details, please visit http://imagine.enpc.fr/.