科技报告详细信息
Comparing GPU Implementations of Bilateral and Anisotropic Diffusion Filters for 3D Biomedical Datasets
Howison, Mark
关键词: 97;    DIFFUSION;    PERFORMANCE;    IMAGE PROCESSING image processing;    MRI;    GPU computing;    CUDA;   
DOI  :  10.2172/983280
RP-ID  :  LBNL-3425E
PID  :  OSTI ID: 983280
Others  :  TRN: US201014%%602
美国|英语
来源: SciTech Connect
PDF
【 摘 要 】

We compare the performance of hand-tuned CUDA implementations of bilateral and anisotropic diffusion filters for denoising 3D MRI datasets. Our tests sweep comparable parameters for the two filters and measure total runtime, memory bandwidth, computational throughput, and mean squared errors relative to a noiseless reference dataset.

【 预 览 】
附件列表
Files Size Format View
RO201704240002298LZ 911KB PDF download
  文献评价指标  
  下载次数:34次 浏览次数:116次