公开(公告)号：US10223612B2

公开(公告)日：2019-03-05

申请号：US15254410

申请日：2016-09-01

Applicant: Microsoft Technology Licensing, LLC

Inventor： Gang Hua ,  Peiran Ren ,  Jiaolong Yang

IPC: G06K9/62 ,  G06K9/00

Abstract: In a video frame processing system, a feature extractor generates, based on a plurality of data sets corresponding to a plurality of frames of a video, a plurality of feature sets, respective ones of the feature sets including features extracted from respective ones of the data sets. A first stage of the feature aggregator generates a kernel for a second stage of the feature aggregator. The kernel is adapted to content of the feature sets so as to emphasize desirable ones of the feature sets and deemphasize undesirable ones of the feature sets. In the second stage of the feature aggregator the kernel generated by the first stage is applied to the plurality of feature sets to generate a plurality of significances corresponding to the plurality of feature sets. The feature sets are weighted based on corresponding significances and weighted feature sets are aggregated to generate an aggregated feature set.

公开(公告)号：US20150193967A1

公开(公告)日：2015-07-09

申请号：US14662749

申请日：2015-03-19

Applicant: Microsoft Technology Licensing, LLC

Inventor： Jiaping Wang ,  Peiran Ren ,  Baining Guo ,  Minmin Gong ,  Xin Tong ,  Stephen S. Lin

IPC: G06T15/50 ,  G06N99/00

CPC classification number: G06T15/506 ,  G06N99/005 ,  G06T15/80

Abstract: Some implementations disclosed herein provide techniques and arrangements to render global light transport in real-time or near real-time. For example, in a pre-computation stage, a first computing device may render points of surfaces (e.g., using multiple light bounces and the like). Attributes for each of the points may be determined. A plurality of machine learning algorithms may be trained using particular attributes from the attributes. For example, a first machine learning algorithm may be trained using a first portion of the attributes and a second machine learning algorithm may be trained using a second portion of the attributes. The trained machine learning algorithms may be used by a second computing device to render components (e.g., diffuse and specular components) of indirect shading in real-time.

Abstract translation: 本文公开的一些实施例提供了实时或接近实时地呈现全局光传输的技术和布置。 例如，在预计算阶段，第一计算设备可以渲染表面的点（例如，使用多个光反射等）。 可以确定每个点的属性。 可以使用来自属性的特定属性来训练多个机器学习算法。 例如，可以使用属性的第一部分来训练第一机器学习算法，并且可以使用属性的第二部分来训练第二机器学习算法。 经过训练的机器学习算法可以被第二计算设备用于实时地呈现间接着色的组件（例如，漫反射和镜面分量）。

公开(公告)号：US09684996B2

公开(公告)日：2017-06-20

申请号：US14662749

申请日：2015-03-19

Applicant: Microsoft Technology Licensing, LLC

Inventor： Jiaping Wang ,  Peiran Ren ,  Baining Guo ,  Minmin Gong ,  Xin Tong ,  Stephen S. Lin

IPC: G06T15/50 ,  G06N99/00 ,  G06T15/80

CPC classification number: G06T15/506 ,  G06N99/005 ,  G06T15/80

Abstract: Some implementations disclosed herein provide techniques and arrangements to render global light transport in real-time or near real-time. For example, in a pre-computation stage, a first computing device may render points of surfaces (e.g., using multiple light bounces and the like). Attributes for each of the points may be determined. A plurality of machine learning algorithms may be trained using particular attributes from the attributes. For example, a first machine learning algorithm may be trained using a first portion of the attributes and a second machine learning algorithm may be trained using a second portion of the attributes. The trained machine learning algorithms may be used by a second computing device to render components (e.g., diffuse and specular components) of indirect shading in real-time.