This paper presents the nearest neighbor value (NNV) algorithm for high resolution (H.R.) image interpolation. The difference between the proposed algorithm and conventional nearest neighbor algorithm is that the concept applied, to estimate the missing pixel value, is guided by the nearest value rather than the distance. In other words, the proposed concept selects one pixel, among four direct...

Image interpolation is one of key contents in image processing. We present an interpolation algorithm based on a rational function model with constraint parameters. Firstly, based on the construction principle of the rational function, the detection threshold is selected through contour analysis. The smooth and non-smooth areas are interpolated by bicubic interpolation and general rational inte...

In this paper, we discuss a new hand-gesture-based application, FlowField, which explores the use of pressure-sensitive multipoint touchpad (multi-touch) interaction. FlowField allows participants to interact using their whole hand with a flow of circulating particles, providing visual and auditory feedback. Limitations of the raw data mapping used in FlowField motivated work on applying interp...

0

n most computer-generated films involving I virtual humans, clothes are simulated as part of the body and have no autonomous motion. In recent years, however, software has been developed to design 2D garment panels interactively and to optimize the layout of the panels on fabric. For example, Hinds and McCartney’ treated garment panels as surfaces of complex 3D shapes. They represented a static...

Single image super-resolution (SISR), as a traditional ill-conditioned inverse problem, has been greatly revitalized by the recent development of convolutional neural networks (CNN). These CNN-based methods generally map low-resolution to its corresponding high-resolution version with sophisticated network structures and loss functions, showing impressive performances. This paper provides new i...

Numerical lagrangian analysis of the Chesapeake Bay can reveal dynamical features not obtainable through analytical means. These features can indicate coherent structures within the Bay, revealing neighboring regions of fluid that have very different behaviors. Given the model-based discrete velocity data of the bay, obtained through the use of the Regional Ocean Modeling System (ROMS), we impl...

Convolutional neural networks have recently demonstrated high-quality reconstruction for single image super-resolution. However, existing methods often require a large number of network parameters and entail heavy computational loads at runtime for generating high-accuracy super-resolution results. In this paper, we propose the deep Laplacian Pyramid Super-Resolution Network for fast and accura...