GPU-accelerated surface denoising and morphing with lattice Boltzmann scheme

Zhao, Ye

doi:10.1109/smi.2008.4547942

Cited by 4 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Current GPU implementations (e.g., [23], [30], [29]) use top-down approaches and differ from our approach from this point of view. A paper by Harris et al [11] is perhaps one of the most interesting early publications reporting a top-down implementation on GPU that is relevant to this study.…”

Section: Ca and 3d On Gpumentioning

confidence: 99%

GPGPU computation and visualization of three-dimensional cellular automata

Gobron

Çöltekin

Bonafos³

et al. 2010

Vis Comput

View full text Add to dashboard Cite

This paper presents a general-purpose simulation approach integrating a set of technological developments and algorithmic methods in cellular automata (CA) domain. The approach provides a general-purpose comput-ing on graphics processor units (GPGPU) implementation for computing and multiple rendering of any direct-neighbor three-dimensional (3D) CA. The major contributions of this paper are: the CA processing and the visualization of large 3D matrices computed in real time; the proposal of an original method to encode and transmit large CA functions to the graphics processor units in real time; and clarification of the notion of top-down and bottom-up approaches to CA that non-CA experts often confuse. Additionally a practical technique to simplify the finding of CA functions is implemented using a 3D symmetric configuration on an interac-tive user interface with simultaneous inside and surface visualizations. The interactive user interface allows for testing the system with different project ideas and serves as a test bed for performance evaluation. To illustrate the flexibility of the proposed method, visual outputs from diverse areas are demonstrated. Computational performance data are also provided to demonstrate the method's efficiency. Results indicate that when large matrices are processed, computations using GPU are two to three hundred times faster than the identical algorithms using CPU. Abstract This paper presents a general-purpose simulation approach integrating a set of technological developments and algorithmic methods in cellular automata (CA) domain. The approach provides a general-purpose computing on graphics processor units (GPGPU) implementation for computing and multi-rendering of any direct-neighbor three dimensional (3D) CA. The major contributions of this paper are; the CA processing and the visualization of large 3D matrices computed in real-time; the proposal of an original method to encode and transmit large CA functions to the graphics processor units in real time; and clarification of the notion of top-down and bottom-up approaches to CA that non-CA experts often confuse. Additionally a practical technique to simplify the finding of CA functions is implemented using a 3D symmetric configuration on an interactive user interface with simultaneous inside and surface visualizations. The interactive user interface allows for testing the system with different project ideas and serves as a test bed for performance evaluation. To illustrate the flexibility of the proposed method, visual outputs from diverse areas are demonstrated. Computational performance data are also provided to demonstrate the method's efficiency. Results indicate that when large matrices are processed, computations using GPU are two to three hundred times faster than the identical algorithms using CPU.

show abstract

Section: Ca and 3d On Gpumentioning

confidence: 99%

GPGPU computation and visualization of three-dimensional cellular automata

Gobron

Çöltekin

Bonafos³

et al. 2010

Vis Comput

View full text Add to dashboard Cite

show abstract

“…In fact, the lattice Boltzmann method has been applied to image filtering by few researchers [15][16][17][18][19][20]. In Ref.…”

Section: Introductionmentioning

confidence: 99%

“…After that, the lattice Boltzmann model for diffusion equation was extended to 3D space for volume smoothing and surface denoising in Refs. [16,17]. In Refs.…”

Section: Introductionmentioning

confidence: 99%

“…[15][16][17][18][19][20] investigate the application of lattice Boltzmann method to image filtering is that this method provides the easily implemented fully parallel algorithms which fulfill the intrinsic features of parallelism. The authors have paid much attention to this advantage, but they omit the efficient difference between different lattice Boltzmann models, such as the difference between D2Q5 and D2Q9, which are two commonly used 2-dimensional models.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of Lattice Boltzmann Method to Image Filtering

Zhang

Shi

2011

J Math Imaging Vis

View full text Add to dashboard Cite

In this paper, lattice Boltzmann D2Q5 (two dimensions and five discrete velocity directions) and D2Q9 (two dimensions and nine discrete velocity directions) models are used to solve Perona-Malik equation, which is widely used in image filtering. A set of images added three types of noise are processed using these models. Then the processed images are compared in aspects of peak signal to noise ratio (PSNR) and visual effect. The comparison show that two models have almost the same filtering effect. Simultaneously, it is validated that D2Q5 model is more efficient. Other findings are: (1) D2Q5 and D2Q9 models are more effective in dealing with some images than others; (2) salt and pepper noise is relatively difficult to remove compared with gaussian noise and speckle noise; (3) lattice Boltzmann method shows good stability in the image filtering.

show abstract