Sciweavers

17 search results - page 2 / 4
» Do Ambiguous Reconstructions Always Give Ambiguous Images
Sort
View
3DPVT
2006
IEEE
202views Visualization» more  3DPVT 2006»
14 years 1 months ago
Visual Shapes of Silhouette Sets
Shape from silhouette methods are extensively used to model dynamic and non-rigid objects using binary foreground-background images. Since the problem of reconstructing shapes fro...
Jean-Sébastien Franco, Marc Lapierre, Edmon...
ICIP
2009
IEEE
13 years 5 months ago
Locality preserving constraints for super-resolution with neighbor embedding
In this paper, we revisit the manifold assumption which has been widely adopted in the learning-based image superresolution. The assumption states that point-pairs from the high-r...
Bo Li, Hong Chang, Shiguang Shan, Xilin Chen
PAMI
2011
13 years 2 months ago
Linear Local Models for Monocular Reconstruction of Deformable Surfaces
—Recovering the 3D shape of a nonrigid surface from a single viewpoint is known to be both ambiguous and challenging. Resolving the ambiguities typically requires prior knowledge...
Mathieu Salzmann, Pascal Fua
CVPR
1999
IEEE
14 years 9 months ago
Critical Motions in Euclidean Structure from Motion
We investigate the motions that lead to ambiguous Euclidean scene reconstructions under several common calibration constraints, giving a complete description of such critical moti...
Fredrik Kahl, Bill Triggs
CVPR
2012
IEEE
11 years 10 months ago
Refractive height fields from single and multiple images
We propose a novel framework for reconstructing homogenous, transparent, refractive height-fields from a single viewpoint. The height-field is imaged against a known planar back...
Qi Shan, Sameer Agarwal, Brian Curless