—Traditional optical flow algorithms rely on consecutive short-exposed images. In this work, we make use of an additional long-exposed image for motion field estimation. Long-e...
Anita Sellent, Martin Eisemann, Bastian Goldlü...
It is well-known that, in unidentifiable models, the Bayes estimation provides much better generalization performance than the maximum likelihood (ML) estimation. However, its ac...
The problem of styling surfaces modeling is tackled. An approach based on section curves fairing is chosen. The concept of template curves is developed for approximating profiles ...
The likelihood models used in probabilistic visual tracking applications are often complex non-linear and/or nonGaussian functions, leading to analytically intractable inference. ...
Finding the sparsest approximation of an image as a sum of basis functions drawn from a redundant dictionary is an NPhard problem. In the case of a dictionary whose elements form ...