Conditional density estimation (CDE) is the task of estimating probability an event conditioned on some inputs. A neural network (NN) can also be used to compute output distribution for continuous-domain, which viewed as extension regression task. Nevertheless, it difficult explicitly approximate a without knowing information its general form priori. In order fit arbitrary conditional distribut...

The resolution of a conventional lens is governed by its numerical aperture (NA) while light-concentration ability f-number (f/#), both which are dependent on the diameter and focal length lens. Hence, these properties for inherently coupled. Here, we show that utilizing principle free-form broadband diffractive optical elements (BDOEs), can create ultra-flat able to concentrate incoming light ...

We describe a free-form stroke-based modeling system where objects are primarily represented by means of variational surfaces. Although similar systems have been described in recent years, our approach achieves both a good performance and reduced surface leak problems by employing a coarse mesh as support for constraint points. The prototype implements an adequate set of modeling operations, “u...