Approximate nearest neighbor queries revisited
SCG '97 Proceedings of the thirteenth annual symposium on Computational geometry
An optimal algorithm for approximate nearest neighbor searching fixed dimensions
Journal of the ACM (JACM)
Closest-point problems simplified on the RAM
SODA '02 Proceedings of the thirteenth annual ACM-SIAM symposium on Discrete algorithms
Low latency photon mapping using block hashing
Proceedings of the ACM SIGGRAPH/EUROGRAPHICS conference on Graphics hardware
High Dimensional Similarity Search With Space Filling Curves
Proceedings of the 17th International Conference on Data Engineering
Photon mapping on programmable graphics hardware
Proceedings of the ACM SIGGRAPH/EUROGRAPHICS conference on Graphics hardware
Real-time KD-tree construction on graphics hardware
ACM SIGGRAPH Asia 2008 papers
An efficient GPU-based approach for interactive global illumination
ACM SIGGRAPH 2009 papers
Hardware-accelerated global illumination by image space photon mapping
Proceedings of the Conference on High Performance Graphics 2009
Stochastic progressive photon mapping
ACM SIGGRAPH Asia 2009 papers
GPU-Accelerated Nearest Neighbor Search for 3D Registration
ICVS '09 Proceedings of the 7th International Conference on Computer Vision Systems: Computer Vision Systems
Parallel progressive photon mapping on GPUs
ACM SIGGRAPH ASIA 2010 Sketches
Data-Parallel Octrees for Surface Reconstruction
IEEE Transactions on Visualization and Computer Graphics
A graphics hardware accelerated algorithm for nearest neighbor search
ICCS'06 Proceedings of the 6th international conference on Computational Science - Volume Part IV
Toward practical real-time photon mapping: efficient GPU density estimation
Proceedings of the ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games
| Hi-index | 0.00 |
We describe the implementation of a simple method for finding k approximate nearest neighbors (ANNs) on the GPU. While the performance of most ANN algorithms depends heavily on the distributions of the data and query points, our approach has a very regular data access pattern. It performs as well as state of the art methods on easy distributions with small values of k, and much more quickly on more difficult problem instances. Irrespective of the distribution and also roughly of the size of the set of input data points, we can find 50 ANNs for 1M queries at a rate of about 1200 queries/ms.