K
Kurt Debattista
Researcher at University of Warwick
Publications - 171
Citations - 3281
Kurt Debattista is an academic researcher from University of Warwick. The author has contributed to research in topics: Rendering (computer graphics) & Real-time rendering. The author has an hindex of 26, co-authored 153 publications receiving 2707 citations. Previous affiliations of Kurt Debattista include University of Bristol.
Papers
More filters
Book
Advanced High Dynamic Range Imaging: Theory and Practice
TL;DR: This book provides a practical introduction to the emerging new discipline of high dynamic range imaging that combines photography and computer graphics by providing detailed equations and code that gives the reader the tools needed to experiment with new techniques for creating compelling images.
Proceedings ArticleDOI
Inverse tone mapping
TL;DR: An approximate solution to this problem is proposed that uses median-cut to find the areas considered of high luminance and subsequently applies a density estimation to generate an Expand-map in order to extend the range in the high Luminance areas using an inverse Photographic Tone Reproduction operator.
Journal ArticleDOI
ExpandNet : a deep convolutional neural network for high dynamic range expansion from low dynamic range content
TL;DR: This paper presents a method for generating HDR content from LDR content based on deep Convolutional Neural Networks (CNNs) termed ExpandNet, which accepts LDR images as input and generates images with an expanded range in an end‐to‐end fashion.
Book
Advanced High Dynamic Range Imaging
TL;DR: In this article, the authors explore the methods needed for creating and manipulating HDR content, including the authors' popular HDR Toolbox for MATLAB and give readers the tools they need to develop and experiment with new techniques for creating compelling HDR content.
Proceedings ArticleDOI
A GPU based saliency map for high-fidelity selective rendering
TL;DR: A novel saliency map is presented which exploits the computational performance of modern GPUs and is thus possible to calculate this map in milliseconds, allowing it to be part of a real time rendering system.