• Publications
  • Influence
GPU-ASIFT: A fast fully affine-invariant feature extraction algorithm
TLDR
This paper presents a method that takes advantage of powerful graphics hardware to obtain fully affine-invariant image feature detection and matching, while keeping the accuracy close to that of ASIFT. Expand
  • 23
  • 4
  • PDF
Full Solid Angle Panoramic Viewing by Depth Image Warping on Field Programmable Gate Array
TLDR
A novel approach of cylindrical depth image warping is presented and implemented on a field programmable gate array hardware platform, which can implement a full solid angle panoramic viewing. Expand
  • 10
  • 2
  • PDF
Multi-layer depth peeling via fragment sort
TLDR
We present an accelerated depth peeling algorithm for order-independent transparency rendering on graphics hardware, which achieves up to 8x speed-up over conventional depth-peeling with current generation graphics hardware. Expand
  • 53
  • 1
  • PDF
Octree Rasterization: Accelerating High-Quality Out-of-Core GPU Volume Rendering
TLDR
We present a novel approach for GPU-based high-quality volume rendering of large out-of-core volume data. Expand
  • 14
  • 1
Parallel centerline extraction on the GPU
TLDR
We present a new parallel centerline extraction algorithm suitable for implementation on a GPU to produce highly accurate, 26-connected, one-voxel-thick centerlines at interactive speed. Expand
  • 11
  • 1
  • PDF
Evaluation of autoparallelization toolkits for commodity graphics hardware
TLDR
We evaluate the performance of the OpenACC and Mint toolkits against C and CUDA implementations of the standard PolyBench test suite. Expand
  • 7
  • 1
  • PDF
Evaluating automatically parallelized versions of the support vector machine
TLDR
We have developed a directive‐based approach that converts a gradient‐ascent based training algorithm for the CPU to an efficient graphics processing unit (GPU) implementation. Expand
  • 11
  • 1
  • PDF
Evaluation of Autoparallelization Toolkits for Commodity GPUs
TLDR
In this paper we evaluate the performance of the OpenACC and Mint toolkits against C and CUDA implementations of the standard PolyBench test suite. Expand
  • 6
  • 1
Parallel Marching Blocks: A Practical Isosurfacing Algorithm for Large Data on Many‐Core Architectures
TLDR
We introduce Parallel Marching Blocks: A Practical Isosurfacing Algorithm for Large Data on Many-Core Architectures vertices [LCGR02]. Expand
  • 3
  • 1
Interactively Rendering Dynamic Caustics on GPU
TLDR
In this paper, a new technique is presented for interactive rendering of caustics fully processed on GPU. Expand
  • 3
  • 1
  • PDF