Simon Donné

  • Citations Per Year
Learn More
The problem of camera calibration is two-fold. On the one hand, the parameters are estimated from known correspondences between the captured image and the real world. On the other, these correspondences themselves-typically in the form of chessboard corners-need to be found. Many distinct approaches for this feature template extraction are available, often(More)
Multi-camera triangulation of feature points based on a minimisation of the overall l2 reprojection error can get stuck in suboptimal local minima or require slow global optimisation. For this reason, researchers have proposed optimising the l∞ norm of the l2 single view reprojection errors, which avoids the problem of local minima entirely. In this paper(More)
In two-view stereo matching, the disparity of occluded pixels cannot accurately be estimated directly: it needs to be inferred through, e.g., regularisation. When capturing scenes using a plenoptic camera or a camera dolly on a track, more than two input images are available, and - contrary to the two-view case - pixels in the central view will only very(More)
In this demonstration, we present a new programming framework, Quasar, for heterogeneous programming on CPU and single/multi-GPU. Our programming framework consists of a high-level language that is aimed at relieving the programmer from hardware-related implementation issues that commonly occur in CPU/GPU programming, allowing the programmer to focus on the(More)
Multi-camera triangulation of feature points based on a minimisation of the overall &#x2113;<sub>2</sub> reprojection error can get stuck in suboptimal local minima or require slow global optimisation. For this reason, researchers have proposed optimising the &#x2113;<sub>&#x221E;</sub> norm of the &#x2113;<sub>2</sub> single view reprojection errors, which(More)
We show how pixel-based methods can be applied to a sparse image representation resulting from a superpixel segmentation. On this sparse image representation we only estimate a single motion vector per superpixel, without working on the full-resolution image. This allows the accelerated processing of high-resolution content with existing methods. The use of(More)
Stationarity of reconstruction problems is the crux to enabling convolutional neural networks for many image processing tasks: the output estimate for a pixel is generally not dependent on its location within the image but only on its immediate neighbourhood. We expect other invariances, too. For most pixel-processing tasks, rigid transformations should(More)
Non-rigid structure-from-motion in an on-line setting holds many promises for useful applications, and off-line reconstruction techniques are already very advanced. Literature has only recently started focusing on on-line reconstruction, with only a handful of existing techniques available. Here we propose a novel method of history representation which(More)
Stereomatching is an effective way of acquiring dense depth information from a scene when active measurements are not possible. So-called lightfield methods take a snapshot from many camera locations along a defined trajectory (usually uniformly linear or on a regular grid-we will assume a linear trajectory) and use this information to compute accurate(More)
  • 1