公开(公告)号：US09454806B2

公开(公告)日：2016-09-27

申请号：US14632782

申请日：2015-02-26

Applicant: NVIDIA Corporation

Inventor： Dawid Stanislaw Pajak ,  Yun-Ta Tsai ,  Markus Steinberger

IPC: G06T5/00

CPC classification number: G06T5/002 ,  G06T2207/10024 ,  G06T2207/20021 ,  G06T2207/30201

Abstract: A computer implemented method of performing an approximate-nearest-neighbor search is disclosed. The method comprises dividing an image into a plurality of tiles. Further, for each of the plurality of tiles, perform the following in parallel on a processor: (a) dividing image patches into a plurality of clusters, wherein each cluster comprises similar images patches, and wherein the dividing continues recursively until a size of a cluster is below a threshold value; (b) performing a nearest-neighbor query within each of the plurality of clusters; and (c) performing collaborative filtering in parallel for each image patch, wherein the collaborative filtering aggregates and processes nearest neighbor image patches from a same cluster containing a respective image patch to form an output image.

Abstract translation: 公开了一种执行近似最近邻搜索的计算机实现方法。 该方法包括将图像划分成多个瓦片。 此外，对于多个瓦片中的每一个，在处理器上并行地执行以下操作：（a）将图像斑块分割成多个群集，其中每个群集包括相似的图像块，并且其中所述划分继续递归直到大小为 集群低于阈值; （b）在所述多个聚类中的每一个内执行最近邻查询; 以及（c）对于每个图像补丁并行执行协同过滤，其中所述协同过滤从包含相应图像补丁的相同集群聚集和处理最近邻图像补丁以形成输出图像。

公开(公告)号：US20150206285A1

公开(公告)日：2015-07-23

申请号：US14632782

申请日：2015-02-26

Applicant: NVIDIA Corporation

Inventor： Dawid Stanislaw Pajak ,  Yun-Ta Tsai ,  Markus Steinberger

IPC: G06T5/00

CPC classification number: G06T5/002 ,  G06T2207/10024 ,  G06T2207/20021 ,  G06T2207/30201

Abstract: A computer implemented method of performing an approximate-nearest-neighbor search is disclosed. The method comprises dividing an image into a plurality of tiles. Further, for each of the plurality of tiles, perform the following in parallel on a processor: (a) dividing image patches into a plurality of clusters, wherein each cluster comprises similar images patches, and wherein the dividing continues recursively until a size of a cluster is below a threshold value; (b) performing a nearest-neighbor query within each of the plurality of clusters; and (c) performing collaborative filtering in parallel for each image patch, wherein the collaborative filtering aggregates and processes nearest neighbor image patches from a same cluster containing a respective image patch to form an output image.

Abstract translation: 公开了一种执行近似最近邻搜索的计算机实现方法。 该方法包括将图像划分成多个瓦片。 此外，对于多个瓦片中的每一个，在处理器上并行地执行以下操作：（a）将图像斑块分割成多个群集，其中每个群集包括相似的图像块，并且其中所述划分继续递归直到大小为 集群低于阈值; （b）在所述多个聚类中的每一个内执行最近邻查询; 以及（c）对于每个图像补丁并行执行协同过滤，其中所述协同过滤从包含相应图像补丁的相同集群聚集和处理最近邻图像补丁以形成输出图像。