GPGPU |
General-Purpose Computation Using Graphics Hardware
|
IntroductionGPGPU stands for General-Purpose computation on GPUs. With the increasing programmability of commodity graphics processing units (GPUs), these chips are capable of performing more than the specific graphics computations for which they were designed. They are now capable coprocessors, and their high speed makes them useful for a variety of applications. The goal of this page is to catalog the current and historical use of GPUs for general-purpose computation.
|
This paper by Cabido et al. presents a real-time object tracking algorithm, based on the hybridization of particle filtering (PF) and a multi-scale local search (MSLS) algorithm, for both CPU and GPU architectures. The developed system provides successful results in precise tracking of single and multiple targets in monocular video, operating in real-time at 70 frames per second for 640 × 480 video
resolutions on the GPU, up to 1,100% faster than the CPU version of the algorithm. (Multiscale and local search methods for real time region tracking with particle filters: local search driven by adaptive scale estimation on GPUs. Raul Cabido, Antonio S. Montemayor, Juan Jose Pantrigo, and Bryson R. Payne. Machine Vision and Applications, Springer, 2008.)
Posted: 25 May 2008 [GPGPU /Image And Volume Processing/Computer Vision] # GPGPU Based Image Segmentation Livewire Algorithm Implementation This thesis presents a GPU implementation of the Livewire algorithm. The algorithm is divided in three phases: Sobel or Laplacian filter convolution, image modeling as a grid graph and solving the non-negative weighted edges single-source shortest path problem. In order to calculate the shortest path, an adapted version of the delta-stepping algorithm was developed for GPUs, using CUDA. A critical result analysis shows that intense speedups are seen in image filtering algorithms. On the other hand, the wide use of dependent device memory look-ups has constrained delta-stepping algorithm from achieving higher performance than CPU implementation although a better performance is expected for wider graphs. Besides showing the viability of the Livewire algorithm implementation, this thesis makes available an open-source image segmentation GPU based application, which can be used as example for future GPU algorithm implementations at http://code.google.com/p/gpuwire/.
Posted: 01 Apr 2008 [GPGPU /Image And Volume Processing] # Modal Fourier wavefront reconstruction using GPUs This work
approaches the fundamental problem of accelerating FFT computation by use of
GPUs, in order to apply it to Adaptive Optics, the key for obtaining the
maximum performance from projected ground-based eXtremely Large
Telescopes. A method to efficiently adapt the FFT for the underlying
architecture of GPUs is given. The authors derive a novel FFT method that
alternates base-2 and base-4 decomposition of the bidimensional domain to take
the most from Multiple Render Target extension as they elaborate a very
unusual Pease 8-data "butterfly".
(Modal
Fourier wavefront reconstruction using GPUs J.G. Marichal-Hernandez, J.M.
Rodriguez-Ramos, F. Rosa. La Laguna University. To appear in Journal of
Electronic Imaging.)
Posted: 24 Apr 2007 [GPGPU /Image And Volume Processing] # GPUCV: A free GPU-accelerated library for image processing and computer vision GPUCV is a free
GPU-accelerated library for image processing and computer vision. It offers
an Intel OPENCV-like programming interface for easily porting existing
applications.
A one-page description is available. A longer presentation and discussion
was published at IEEE ICME 2006.
(J.-P. Farrugia, P. Horain, E. Guehenneux, Y. Allusse,
"GPUCV: A framework for image processing acceleration with graphics processors",
CDROM proc. of the
IEEE International Conference on Multimedia & Expo,
July 9-12, 2006, Toronto, Ontario, Canada.)
Posted: 02 Apr 2007 [GPGPU /Image And Volume Processing] # Multi-view stereo vision challenge A multi-view stereo
evaluation has been proposed by Steve Seitz et al. The challenge
involves recovering 3D reconstructions of complete objects from a large
number of views. Among the reported techniques, two out of nine
make an intensive usage of GPUs, both yielding large speedups: the work by
Pons, Keriven
and Labatut that took part in the original competition at CVPR06, and the
work by
Hornung and Kobbelt. Running times, accuracy and completeness of the
methods are reported here.
(Steve Seitz et al.
A
Comparison and Evaluation of Multi-View Stereo Reconstruction
Algorithms, in IEEE Computer Society Conference on Computer Vision
and Pattern Recognition (CVPR), New York, 2006.)
Posted: 07 Nov 2006 [GPGPU /Image And Volume Processing/Computer Vision] # Robust and Efficient Photo-Consistency Estimation for Volumetric 3D Reconstruction The computational power of GPU-based algorithms is receiving increased
attention in research on Computer Vision and 3D stereo reconstruction
from images. In this context one of the most important ingredients for
any 3D stereo reconstruction technique is the estimation of
photo-consistency. This ECCV06 paper presents a new, illumination
invariant photo-consistency measure for high quality, volumetric 3D
reconstruction from calibrated images. In contrast to current standard
methods such as normalized cross-correlation it supports unconstrained
camera setups and non-planar surface approximations. The paper shows how this
measure as well as the other important stages of the volumetric
reconstruction pipeline can be implemented in a highly efficient way by
exploiting current graphics processors. The authors' GPU implementation
achieves speedups up to a factor of 85 in comparison to CPU-based algorithms,
and allows reconstruction of high quality models with computation times of
only a few seconds to minutes, even for large numbers of cameras and
high volumetric resolutions. (
Robust and Efficient Photo-Consistency Estimation for Volumetric 3D Reconstruction.
Alexander Hornung and Leif Kobbelt.
European Conference on Computer Vision (ECCV 2006), LNCS, vol. 3952, Springer, 179-190.)
Posted: 24 Oct 2006 [GPGPU /Image And Volume Processing/Computer Vision] # GPU_KLT: A GPU-based Implementation of the Kanade-Lucas-Tomasi Feature Tracker GPU_KLT is an implementation (using OpenGL/Cg) of the popular KLT feature
tracker which runs primarily on the graphics processing unit (GPU). The
GPU-based implementation emulates Stan Birchfield's KLT implementation
of the original algorithm proposed by Kanade, Lucas and Tomasi (1991).
GPU_KLT tracks approximately 1000 feature points within 1024x768 resolution
video at 30 Hz on an ATI 1900 XT and at 25 Hz on a Nvidia Geforce 7900 GTX.
It can be used for real-time computer vision systems involving object
detection, structure from motion, robot navigation and video surveillance.
Source code is available for research use on our webpage.
( GPU_KLT webpage
Sudipta N Sinha, Jan-Michael Frahm, Marc Pollefeys and Yakup Genc,
"Feature Tracking and Matching in Video Using Programmable Graphics Hardware",
submitted to Machine Vision and Applications, July 2006.)
Posted: 10 Aug 2006 [GPGPU /Image And Volume Processing/Computer Vision] # Toward Real Time Fractal Image Compression Using Graphics Hardware This ISVC 2005 paper by Ugo Erra presents
parallel fractal image
compression using programmable graphics hardware. The main problem of fractal
compression is the very high computing time needed to encode images. The
implementation in this paper exploits the SIMD architecture and inherent
parallelism of recent GPUs to speed up the baseline approach of fractal
encoding. The results presented are achieved on inexpensive and widely available
graphics boards. (Toward Real
Time Fractal Image Compression Using Graphics Hardware. Ugo Erra. In Proceedings
of International Symposium on Visual Computing
2005)
Posted: 17 Oct 2005 [GPGPU /Image And Volume Processing/Compression] # Real-Time, GPU-Based Foreground-Background Segmentation Robust and accurate foreground-background segmentation is a
relatively small but crucial step in several computer vision
applications. It is a key element in surveillance, 3D-modelling from
silhouettes, motion capture, or gesture analysis for human-computer
interaction (HCI). For several of these, real-time processing is of main
importance and thus should be extremely fast. This work by Andreas Griesser of ETH
Zurich proposes a high-speed GPU-based implementation that processes image
sequences in less than 4ms per frame and frees the CPU from this
processing step altogether. Resulting segmentation exhibits compactness
and smoothness in foreground areas as well as for inter-frame temporal
contiguity. (Project
homepage and software download, Andreas Griesser,
Computer Vision Lab, ETH Zuerich.)
Posted: 06 Oct 2005 [GPGPU /Image And Volume Processing] # An Implementation of a FIR Filter on a GPU Alexey Smirnov and Tzi-cker Chiueh from Stony Brook University have
published a technical report describing an implementation of a FIR filter on
a GPU. The results of the performance evaluation using a Geforce 6600 video
card and a Pentium 4-HT 3.2 GHz-based PC indicate that the GPU
implementation is better than the SSE-optimized CPU implementation for
certain input parameters. (FIR on GPU project. Report:
An Implementation of a
FIR Filter on a GPU (warning: postscript). Technical Report, Experimental Computer Systems Lab, Stony Brook University, 2005.)
Posted: 19 Sep 2005 [GPGPU /Image And Volume Processing] # FxPlug GPU Image Processing API Launched The FxPlug API allows Mac OS X developers to write OpenGL
based image processing plugins for Apple's Motion video effects software. Designed to run on ARB_fragment_program capable hardware, it allows chains of complex effects to be run entirely on the GPU. With over 100 GPU filters and generators already running within Motion, this is well worth a look. (http://developer.apple.com/appleapplications/fxplugsdk.html)
Posted: 26 May 2005 [GPGPU /Image And Volume Processing] # This project focused on two supportive information techniques for virtual TV studio environments using a back projected screen and real time video composition on the GPU. In traditional TV, studios use blue or green background chroma-key for video composition. Therefore the actors cannot see the final composite without a preview monitor. Pointing at objects on the background image is especially difficult, requiring experience and rehearsal. In this system, the actors can see and point at supportive information displays such as computer-generated backgrounds, virtual actors, reading scripts and/or final composites behind them. To compose the computer graphics into the free area on the screen, a special real-time GPU-based video rendering program has been developed. (http://akihiko.shirai.as/projects/LuminaStudio/)
Posted: 26 May 2005 [GPGPU /Image And Volume Processing] # RoboGamer: Development of robotic TV game player using haptic interface and GPU image recognition "RoboGamer" is a robotic system which is able to play a video game together with a human player. This project realized a physically connected friendly computer player with a simple robotic system that is composed of a video camera, wire based force feedback display SPIDAR and fast GPU image recognition software without any modification of the original video game system. RoboGamer has three functions: autonomous play; augmented effects like force feedback and/or rich graphics added to original old video games; and collaboration play with A.I. and human player via force feedback on the joystick. (http://akihiko.shirai.as/projects/RoboGamer/)
Posted: 26 May 2005 [GPGPU /Image And Volume Processing/Computer Vision] # GPU-Accelerated Computed Tomography The task of reconstructing an object from its projections via tomographic methods is a time-consuming process due to the vast complexity of the data. GPUs offer an affordable alternative to proprietary ASICs and FPGAs.
Fang Xu and Klaus Mueller
at Stony Brook
University have shown that the latest generation of GPUs can be exploited to perform both analytical and iterative reconstruction from X-ray and functional imaging data at clinical rates and high quality. Visualization of the
reconstructed object is easily achieved since the object already resides in the graphics hardware, allowing one to run a visualization module at any time to view the reconstruction results. Their implementation allows speedups of 1-2 orders of magnitude over software implementations, at
comparable image quality. (Link
to the project page)
Posted: 05 May 2005 [GPGPU /Image And Volume Processing] # Ne@tware Player 2005 for Video Post-Processing and Effects Ne@tware Player 2005 is a shader player. It supports video over a model with real-time visual special effects using programmable HLSL shaders. Its multithreaded media engine supports media mixing, media codecs, and Shader Model 3.0. Developers can also design and test their own HLSL shaders and FX effects in Ne@tware Player 2005.
Posted: 21 Mar 2005 [GPGPU /Image And Volume Processing] # Hardware Efficient PDE Solvers in Quantized Image Processing This thesis by Robert Strzodka describes the design of robust quantized schemes and their hardware efficient implementation on data-stream-based architectures for PDE-based image processing. The focus lies on enhancing both performance and accuracy by an efficient use of appropriate hardware resources. Quantized schemes which, despite roundoff errors, preserve the qualitative behavior of the continuous models are constructed, and examined on different GPUs, a FPGA and a reconfigurable array processor. The pros and cons of the hardware designs and the memory gap problem are discussed in detail. (Hardware Efficient PDE Solvers in Quantized Image Processing. Robert Strzodka. PhD thesis, University of Duisburg-Essen, 2004.)
Posted: 20 Mar 2005 [GPGPU /Image And Volume Processing] # Interactive marker-less tracking of human limbs This paper by Rao et al. at UNC Charlotte describes an algorithm to track human limbs at interactive rates without using markers. 3d point cloud data is derived from a modified visual hull algorithm. This data is fed into a particle filtering algorithm that runs on the GPU. The tracking system runs at interactive rates. ( Interactive marker-less tracking of human limbs. Rao S., Hodges L.F to be submitted to Transactions on Visualization and Computer Graphics.)
Posted: 20 Mar 2005 [GPGPU /Image And Volume Processing/Computer Vision] # Fourier Volume Rendering on the GPU Using a Split-Stream FFT This paper by Jansen et al. describes how to utilize current commodity graphics hardware to perform Fourier volume rendering directly on the GPU. The paper presents a novel implementation of the Fast Fourier Transform: This Split-Stream-FFT maps the recursive structure of the FFT to the GPU in an efficient way. Additionally, high-quality resampling within the frequency domain is discussed. The implementation enables visualization of large volumetric data sets at interactive frame rates on a mid-range computer system. (Fourier Volume Rendering on the GPU Using a Split-Stream FFT)
Posted: 28 Feb 2005 [GPGPU /Image And Volume Processing] # Image Registration by a Regularized Gradient Flow To correlate the intensities in two images an energy functional is successively minimized in a variational setting. The gradient flow formulation makes use of a robust multi-scale regularization, an efficient multi-grid solver and an adaptive time-step control. On the GPU the multi-scale maps to a packed multi-grid pyramid with several scales per grid level. The algorithm uses three nested loops: the regularized multi-scale descent, the iterative solution of the gradient flow PDE, and on the third level the multi-grid smoother and the adaptive time-step iteration.
( Image Registration by a Regularized Gradient Flow - A Streaming Implementation in DX9 Graphics Hardware. Robert Strzodka, Marc Droske and Martin Rumpf Computing, 73(4), 373-389, Springer, 2004.)
Posted: 05 Jan 2005 [GPGPU /Image And Volume Processing] # Real-Time Motion Estimation and Visualization on Graphics Cards This paper by Strzodka and Garbe presents a tool for real-time visualization of motion features in 2D image sequences. The motion is estimated through an eigenvector analysis of the spatio-temporal structure tensor at every pixel location. Post-processing in the form of coloring, blending, threshholding, fading and smoothing helps to select the desired motion features for display. The paper demonstrates several examples of test sequences containing people moving at different velocities. These people are visually marked in the real-time display of the image sequence. The tool is also applied to angiography sequences to emphasize the blood flow and its distribution. The implementation uses DX9 graphics hardware and centers around a vectorized version of the Jacobi method for matrix diagonalization. (Real-Time Motion Estimation and Visualization on Graphics Cards. Robert Strzodka and Christoph Garbe in Proceedings of Visualization 2004, pages 545-552, 2004)
Posted: 27 Nov 2004 [GPGPU /Image And Volume Processing] # |
Categories
|
