Recent Activities


POPART EU project started

posted 18 Jan 2015, 07:14 by Simone Gasparini

The POPART project has officially started during the kick-off meeting in Oslo this week. The project is about previsualization of visual special effects in filmmaking. Here is the official web site.

Paper accepted at MMSys 2015

posted 18 Jan 2015, 07:12 by Simone Gasparini

The paper "The Toulouse Vanishing Points Dataset" has been accepted in the Dataset Track at MMSys 2015 to be held in Portland. 

New pages

posted 23 Jul 2012, 02:21 by Simone Gasparini

I added two new pages describing the latest projects I've been involved in. Check them out:


Research Activity updated

posted 10 Jul 2012, 10:27 by Simone Gasparini

I added some new videos about my current activities at Gipsa Lab

IJCV Paper online

posted 3 Apr 2011, 09:21 by Simone Gasparini

The paper "Line localization from single catadioptric images" has been (finally...) published online here.

Some updates...

posted 24 Jun 2010, 06:17 by Simone Gasparini

I updated some info in the research section and fixed some minor bugs. 

Work in progress on the website

posted 28 Jul 2009, 06:19 by Simone Gasparini

I've restored most of the things from the old website, now you can see all the images. I must fix all the links to publication, though. I added two new pages with demos of the smart camera "hands up" project; it will take a while to load them since the swf videos are heavy. I'll fix this too.
Check them out:
Stay tuned! :-)

ICCV09 paper accepted

posted 10 Jun 2009, 04:29 by Simone Gasparini

The paper on catadioptric calibration from planar grids submitted to the International Conference on Computer Vision ICCV09 has been accepted.

Here is the details of the paper

S. Gasparini, P. Sturm, J.P. Barreto (2009), Plane-Based Calibration of Central Catadioptric Cameras, to apper in Proceedings of the International Conference of Computer Vision ICCV09.

Abstract
We present a novel calibration technique for all central catadioptric cameras using images of planar grids. We adopted the well-known sphere camera model to describe the catadioptric projection. We show that, using the so-called lifted coordinates, a linear relation mapping the grid points to the corresponding points on the image plane can be written as a 6x6 matrix Hcata, which acts like the classical 3x3 homography for perspective cameras. We show how to compute the image of the absolute conic (IAC) from at least 3 homographies and how to recover from it the intrinsic parameters
of the catadioptric camera. In the case of paracatadioptric cameras one such homography is enough to estimate the IAC, thus allowing the calibration from a single image.

Paper on multiview matching tensor published

posted 8 Jun 2009, 05:46 by Simone Gasparini

The paper on multiview matching tensor has been published as a chapter in the book "Tensors in Image Processing and Computer Vision" by Springer.

Here is the full reference
S. Gasparini, P. Sturm (2009), Multi-View Matching Tensors from Lines for General Camera Models, In S. Aja-Fernández, R. de Luis García, D.Tao, and X. Li, editors, Tensors in Image Processing and Computer Vision, Advances in Pattern  Recognition, pages 198--214. Springer London, 1st edition, May 2009.10.1007/978-1-84882-299-3_9

and the abstract
General camera models relax the constraint on central projection and characterize cameras as mappings between each pixel and the corresponding projection rays. This allows to describe most cameras types, including classical pinhole cameras, cameras with various optical distortions, catadioptric cameras and other acquisition devices. We deal with the structure from motion problem for such general models. We first consider an hierarchy of general cameras first introduced in [28] where the cameras are described according to the number of points and lines that have a non-empty intersection with all the projection rays. Then we propose a study of the multi-view geometry of such cameras and a new formulation of multi-view matching tensors working for projection rays crossing the same 3D line, the counterpart of the fundamental matrices and the multifocal tensors of the standard perspective cameras. We also delineate a method to estimate such tensors and recover the motion between the views.

Under Construction

posted 14 May 2009, 02:50 by Simone Gasparini   [ updated 14 May 2009, 08:26 ]

I've just started to migrate from the old googlepage site and build the new site. It'll take a while... be patient! :-)

1-10 of 10