Abstract: A method of representing a space of handwriting stroke styles includes representing writer-, character- and writer-character-level style variations within a recurrent neural network (RNN) model using decoupled style descriptors (DSD) that model the style variations such that character style variations depend on writer style.

Abstract: A method of representing a space of handwriting stroke styles includes representing writer-, character- and writer-character-level style variations within a recurrent neural network (RNN) model using decoupled style descriptors (DSD) that model the style variations such that character style variations depend on writer style.

Abstract: A lenticular display device that is effective in increasing both perceived angular resolution and spatial resolution. These desirable results are achieved by modifying the lenslet array to better match the content of a given light field. An optimization algorithm or method (which may be implemented with software run on a computing device) is provided that analyzes an input light field and computes an optimal lenslet size, shape, and arrangement of sets of lenslets across the width of the array to better (or even best) match the input light field given a set of output parameters. The resulting lenticular display device (or print) shows higher detail and smoother motion parallax compared with fixed-size lens arrays. The usefulness of these content-adaptive lenticular prints has been demonstrated or proven using rendered simulations, by generating 3D-printed lens arrays according to the present description, and with user studies.

Abstract: Approaches presented herein enable to the interactive exploration of digital videos. The videos can include digital videos that have casually been captured by consumer devices, such as mobile phone cameras, tablets, and the like. Robust methods and systems are presented that enable such digital videos to be explored in interesting and advantageous ways, including transitions and other such features.

Abstract: A lenticular display device is described that is effective in increasing both perceived angular resolution and spatial resolution. These desirable results are achieved by modifying the lenslet array to better match the content of a given light field. An optimization algorithm or method (which may be implemented with software run on a computing device) is provided that analyzes an input light field and computes an optimal lenslet size, shape, and arrangement of sets of lenslets across the width of the array to better (or even best) match the input light field given a set of output parameters. The resulting lenticular display device (or print) shows higher detail and smoother motion parallax compared with fixed-size lens arrays. The usefulness of these content-adaptive lenticular prints has been demonstrated or proven using rendered simulations, by generating 3D-printed lens arrays according to the present description, and with user studies.