3D reconstruction from an unordered set of images may fail due to incorrect epipolar geometries (EG) between image pairs arising from ambiguous feature correspondences. Previous m...
Adaptive sparse coding methods learn a possibly overcomplete set of basis functions, such that natural image patches can be reconstructed by linearly combining a small subset of t...
In this paper a novel direction adaptive super-resolution (SR) image reconstruction method is proposed. The proposed maximum a-posteriori (MAP) based estimator uses gradient direc...
We propose a global optimization framework for 3D shape reconstruction from sparse noisy 3D measurements frequently encountered in range scanning, sparse featurebased stereo, and ...
We investigate the properties of a metric between two distributions, the Earth Mover's Distance (EMD), for content-based image retrieval. The EMD is based on the minimal cost ...