A structure for implementing lapped transforms with time-varying block sizes is presented which allows full orthogonality of the transient transforms. The formulation is based on ...
Intensity-based methods work well for multi-modal image registration owing to their effectiveness and simplicity, but the computation for geometric transforms is a heavy load. To ...
The structure-from-motion problem has been extensively studied in the field of computer vision. Yet, the bulk of the existing work assumes that the scene contains only a single mo...
This paper presents a novel spatial texture prediction method based on non-negative matrix factorization. As an extension of template matching, approximation based iterative textu...