parallel recursive filtering for date: image processing · parallel recursive filtering for image...

1
Abstract: In this talk, we will present a variety of recent advances in parallel recursive filtering on the GPU. Recursive filtering is one of the key operations in image processing. It can be used, for example, to invert the effect of convolutions, to enable highest-quality image interpolation and antialiasing for rendering, and in the fastest implementations of image blurring. The talk will cover the content of two SIGGRAPH Asia publications. One of them focuses on how to break the dependency chain to increase the amount of exposed parallelism while minimizing bandwidth requirements. The other describes the first method to enable filtering of infinite input extensions exactly. The resulting algorithms offer a complete solution to recursive filtering on the GPU. Our implementations are available for free in open source. About the Speaker: Diego Nehab is an associate professor at the National Institute for Pure and Applied Mathematics (IMPA) in Rio de Janeiro, Brazil. He received BEng and MSc degrees in Computer Science from PUC-Rio in 2000 and 2002, respectively, and a PhD degree (also in Computer Science) from Princeton University in 2007. Before joining IMPA in 2010, he worked as a post-doctoral researcher at Microsoft Research in Redmond. He is interested in most topics related to Computer Graphics, but focuses on parallelism, real-time rendering, and image processing. Date: November 30, 2016 Wednesday 11:00 am Venue: Room 328 Chow Yei Ching Building The University of Hong Kong All are welcome! For enquiries, please call 2859 2180 or email [email protected] Department of Computer Science The University of Hong Kong Parallel Recursive Filtering for Image Processing Diego Nehab National Institute for Pure and Applied Mathematics (IMPA) Rio de Janeiro, Brazil

Upload: trandat

Post on 19-Sep-2018

214 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Parallel Recursive Filtering for Date: Image Processing · Parallel Recursive Filtering for Image Processing Diego Nehab National Institute for Pure and Applied Mathematics (IMPA)

Abstract:

In this talk, we will present a variety of recent advances in parallel recursive filtering on the GPU. Recursive filtering is one of the key operations in image processing. It can be used, for example, to invert the effect of convolutions, to enable highest-quality image interpolation and antialiasing for rendering, and in the fastest implementations of image blurring. The talk will cover the content of two SIGGRAPH Asia publications. One of them focuses on how to break the dependency chain to increase the amount of exposed parallelism while minimizing bandwidth requirements. The other describes the first method to enable filtering of infinite input extensions exactly. The resulting algorithms offer a complete solution to recursive filtering on the GPU. Our implementations are available for free in open source.

About the Speaker:

Diego Nehab is an associate professor at the National Institute for Pure and Applied Mathematics (IMPA) in Rio de Janeiro, Brazil. He received BEng and MSc degrees in Computer Science from PUC-Rio in 2000 and 2002, respectively, and a PhD degree (also in Computer Science) from Princeton University in 2007. Before joining IMPA in 2010, he worked as a post-doctoral researcher at Microsoft Research in Redmond. He is interested in most topics related to Computer Graphics, but focuses on parallelism, real-time rendering, and image processing.

Date:November 30, 2016Wednesday11:00 am

Venue:Room 328Chow Yei Ching BuildingThe University of Hong Kong

All are welcome!For enquiries, please call 2859 2180 or email [email protected] of Computer ScienceThe University of Hong Kong

Parallel Recursive Filtering for Image Processing

Diego NehabNational Institute for Pure and Applied Mathematics (IMPA)Rio de Janeiro, Brazil