Boosting is a remarkably simple and flexible classification algorithm with widespread applications in computer vision. However, the application of boosting to nonEuclidean, infini...
This paper addresses the problem of video inpainting, that is seamlessly reconstructing missing portions in a set of video frames. We propose to solve this problem proceeding as f...
We consider the problem of estimating the relative orientation of a number of individual photocells -or pixels- that hold fixed relative positions. The photocells measure the inte...
Epipolar geometry and relative camera pose computation for uncalibrated cameras with radial distortion has recently been formulated as a minimal problem and successfully solved in...
Recent work in object categorization often uses local image descriptors such as SIFT to learn and detect object categories. Such descriptors explicitly code local appearance and h...
An approach for incremental learning of a 3D scene from a single static video camera is presented in this paper. In particular, we exploit the presence of casual people walking in...
Diego Rother, Kedar A. Patwardhan, Guillermo Sapir...
Indisputably Normalized Cuts is one of the most popular segmentation algorithms in computer vision. It has been applied to a wide range of segmentation tasks with great success. A...
Most previous motion deblurring methods restore the degraded image assuming a shift-invariant linear blur filter. These methods are not applicable if the blur is caused by spatial...
This paper presents a technique for determining an object's shape based on the similarity of radiance changes observed at points on its surface under varying illumination. To...