TU Darmstadt / ULB / TUbiblio

Rapid, Detail-Preserving Image Downscaling

Weber, Nicolas and Waechter, Michael and Amend, Sandra C. and Guthe, Stefan and Goesele, Michael (2016):
Rapid, Detail-Preserving Image Downscaling.
In: ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia), ACM, [Online-Edition: http://sa2016.siggraph.org],
[Article]

Abstract

Image downscaling is arguably the most frequently used image processing tool. We present an algorithm based on convolutional filters where input pixels contribute more to the output image the more their color deviates from their local neighborhood, which preserves visually important details. In a user study we verify that users prefer our results over related work. Our efficient GPU implementation works in real-time when downscaling images from 24M to 70k pixels. Further, we demonstrate empirically that our method can be successfully applied to videos.

Item Type: Article
Erschienen: 2016
Creators: Weber, Nicolas and Waechter, Michael and Amend, Sandra C. and Guthe, Stefan and Goesele, Michael
Title: Rapid, Detail-Preserving Image Downscaling
Language: English
Abstract:

Image downscaling is arguably the most frequently used image processing tool. We present an algorithm based on convolutional filters where input pixels contribute more to the output image the more their color deviates from their local neighborhood, which preserves visually important details. In a user study we verify that users prefer our results over related work. Our efficient GPU implementation works in real-time when downscaling images from 24M to 70k pixels. Further, we demonstrate empirically that our method can be successfully applied to videos.

Journal or Publication Title: ACM Transactions on Graphics (Proceedings of SIGGRAPH Asia)
Publisher: ACM
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Graphics, Capture and Massively Parallel Computing
Exzellenzinitiative > Graduate Schools > Graduate School of Computational Engineering (CE)
Exzellenzinitiative > Graduate Schools
Exzellenzinitiative
Event Title: SIGGRAPH Asia
Event Location: Macao
Event Dates: December 5-8th, 2016
Date Deposited: 21 Sep 2016 11:30
Official URL: http://sa2016.siggraph.org
Related URLs:
Export:

Optionen (nur für Redakteure)

View Item View Item