Consider two views of a multi-body scene consisting of planar bodies moving in pure translation one relative to the other. We show that the fundamental matrices, one per body, liv...
This paper addresses the problem of recovering structure and motion from silhouettes. Silhouettes are projections of contour generators which are viewpoint dependent, and hence do...
Projection matrices from projective spaces ? to ? have long been used in multiple-view geometry to model the perspective projection created by the pin-hole camera. In this work we...
In this paper, parallelepipeds and their use in camera calibration and 3D reconstruction processes are studied. Parallelepipeds naturally characterize rigidity constraints present...
Intrinsic images are a useful midlevel description of scenes proposed by Barrow and Tenenbaum [1]. An image is decomposed into two images: a reflectance image and an illumination ...
We introduce a new graph-theoretic approach to image segmentation based on minimizing a novel class of `mean cut' cost functions. Minimizing these cost functions corresponds ...
This paper presents a novel landmark-based shape deformation method. This method effectively solves two problems inherent in landmark-based shape deformation: (a) identification o...
Self-calibration using pure rotation is a well-known technique and has been shown to be a reliable means for recovering intrinsic camera parameters. However, in practice, it is vir...
Leslie Wang, Sing Bing Kang, Heung-Yeung Shum, Gua...
In this paper, we study the structure from motion problem as a constrained nonlinear least squares problem which minimizes the so called reprojection error subject to all constrai...