This project is read-only.
Evento: Palestra no Departamento de Ciência da Computação do ETH - Swiss Federal Institute of Technology Zurich
Data: 3 de Junho de 2011
Local: Departamento de Ciência da Computação do ETH - Swiss Federal Institute of Technology Zurich
Site do Evento:

Resumo do Evento
O Swiss Federal Institute of Technology Zurich (ETH) é um dos mais conceituados institutos de pesquisa da Europa. No dia 3 de junho de 2011, o Professor Manuel visitou o Departamento de Ciência da Computação do ETH e proferiu palestra para o Grupo de Pesquisa do Professor Marc Pollefeys. A visita contribuiu para divulgação dos trabalhos de pesquisa desenvolvidos no Instituto de Informática da UFRGS, e permitiu uma interação com professores e estudantes de pós-graduação do ETH. A seguir, temos um resumo da palestra proferida pelo Professor Manuel.

Resumo da Palestra

Domain Transform for Edge-Aware Image and Video Processing

I will present a new approach for performing high-quality edge-preserving filtering of images and videos in real time. Our solution is based on a transform that defines an isometry between curves on the 2D image manifold in 5D and the real line. This transform preserves the geodesic distance between points on these curves, adaptively warping the input signal so that 1D edge-preserving filtering can be efficiently performed in linear time. I will demonstrate three realizations of 1D edge-preserving filters, and show how to produce high-quality 2D edge-preserving filters by iterating 1D-filtering operations. Our approach has several desirable features: the use of 1D operations leads to considerable speedups over existing techniques and potential memory savings; its computational cost is not affected by the choice of the filter parameters; and it is the first edge-preserving filter to work on color images at arbitrary scales in real time, without resorting to subsampling or quantization. I will demonstrate the versatility of our domain transform and edge-preserving filters on several real-time image and video processing tasks including edge-preserving filtering, depth-of-field effects, stylization, recoloring, colorization, detail enhancement, and tone mapping.

This is joint work with Eduardo Gastal.

Last edited Jun 25, 2011 at 9:22 PM by ManuelMenezes, version 1


No comments yet.