VidCNN - Learning Blind Video Denoising

We propose a novel Convolutional Neural Network (CNN) for Video Denoising called VidCNN, which is capable to denoise videos without prior knowledge on the noise distribution (Blind). VidCNN is a flexible model, since it tackles multiple noise types, artificial and real. The CNN architecture uses a combination of spatial and temporal filtering,...

Designing with transparent lighting: A Do-It-Yourself approach

Electroluminescent material is a light emitting electrically powered composite which consists of a stacked sequence of various specific materials. At the faculty of Industrial Design Engineering there is always an interest for the development of new materials. Yet there is a knowledge gap between the theory and the practical DIY fabrication of...

Experience-enablers: A research on how different types of acquisitions can contribute to people’s subjective well-being

This thesis consists of two main parts: Part 1- A qualitative user study of ten interviews, referred to as Study 1, that is addressed in ‘Violins, ovens and hiking shoes: How experience enablers affect people’s subjective well-being in comparison to material- and experiential acquisitions’ Part 2- A quantitative user study of 209 participants...

The Production of ON-Chip Colourstripefilters: For use in solid state image sensors

The principle of making a colourfilter is easy; first make a filter, then colour it. We are however dealing with a process with an enormous amount of variables, which each of them needs investigation. Moreover, the process is in need of alternative "raw material" sources, for both practical and strategic reasons. In the course of this treatise,...

Wegenplanning en ruimtelijke planning