We consider the problem of nonrigid shape and motion recovery from point correspondences in multiple perspective views. It is well known that the constraints among multiple views o...
Abstract. We introduced an algorithm for sequence alignment, based on maximizing local space-time correlations. Our algorithm aligns sequences of the same action performed at diffe...
We describe a new region descriptor and apply it to two problems, object detection and texture classification. The covariance of d-features, e.g., the three-dimensional color vecto...
Abstract. Foreground and background segmentation is a typical problem in computer vision and medical imaging. In this paper, we propose a new learning based approach for 3D segment...
Abstract. We are interested in diffusion PDE's for smoothing multi-valued images in an anisotropic manner. By pointing out the pros and cons of existing tensor-driven regulari...
This paper presents a learning based approach to tracking articulated human body motion from a single camera. In order to address the problem of pose ambiguity, a one-to-many mappi...
Abstract. We present a new approach for self-calibrating the distortion function and the distortion center of cameras with general radially symmetric distortion. In contrast to mos...
Abstract. Conventional photometric stereo has a fundamental limitation that the scale of recovered geometry is limited to the resolution of the input images. However, surfaces that...
One of the most exciting advances in early vision has been the development of efficient energy minimization algorithms. Many early vision tasks require labeling each pixel with som...
Richard Szeliski, Ramin Zabih, Daniel Scharstein, ...
Abstract. In this paper, we introduce background cut, a high quality and realtime foreground layer extraction algorithm. From a single video sequence with a moving foreground objec...