You can now download the software we use to generate the CVTs of Kinovis models! CVT project page. This source code aims to generate CVTs from triangle meshes and point clouds. The code is made available as is without any warranty; without even the implied warranty of fitness for a…
Estimation of Human Body Shape in Motion with Wide Clothing European Conference on Computer Vision, 2016 Jinlong Yang, Jean-Sébastien Franco, Franck Hétroy-Wheeler, and Stefanie Wuhrer Estimating 3D human body shape in motion from a sequence of unstructured oriented 3D point clouds is important for many applications. We propose the first…
Adnane Boukhayma, one of Morpheo’s phd students used data captured in Kinovis for his work on Animation Synthesis from 4D sequences. You can download the full paper here
We added textures to the meshes in the real-time demo. The textures are built from the views of 60 cameras. This requires to compress 60 4Mpix images to less than 10 MB so that the NIC and GPU of the rendering machine do not get overloaded. Therefore, the textures are…
The Kinovis team will take part in “La Fête de la Science” next week. 8 groups of teenagers will visit the platform and discover the world of 3D reconstruction and 4D modeling. More details (in French)
Thibaud Michel, PhD student in the Tyrex & Necs teams used Kinovis to acquire ground truth data for Attitude Estimation for Pedestrian Navigation with Smartphones. His paper was accepted at IPIN 2015. This is the first paper using Kinovis Mocap system to be accepted! For more information, please visit the project website.…
ANIMO ( A#1trailer 2014 et A#2maquette 2015) from gwendaline bachini on Vimeo. The prototype of A#2 willl be displayed at EXPERIMENTA 2015, in Grenoble. A#2 is an interactive installation created by Gwendaline Bacchini with the help of 4DView Solution and SIP Conseil, as well as the Morpheo Team at Inria…
This gallery contains 6 photos.
Here are a few pictures taken during an acquisition in Kinovis. During the geometrical calibration of the 3D reconstruction system, we show lights on a so-called “wand” to all the cameras. To improve the detection, the studio is in the dark. Then we do a “dance” where we move the…
The Kinovis studio was recently extended to perform real-time 3D reconstruction. The previous version of the platform, Grimage, did this, but at a much smaller scale (up to 12 cameras). Kinovis replaces the algorithm based on EPVH with a more scalable version based on QuickCSG. Each of the 60 cameras…
