公开(公告)号：US20180189978A1

公开(公告)日：2018-07-05

申请号：US15738553

申请日：2016-06-24

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Yue DONG ,  Xin TONG ,  Lin LIANG ,  Jian SHI ,  Stephen S. LIN ,  Simon STACHNIAK

IPC: G06T7/90 ,  G06T5/00 ,  G06T7/11 ,  G06T7/136

CPC classification number: G06T7/90 ,  G06T5/008 ,  G06T7/11 ,  G06T7/136 ,  G06T7/40 ,  G06T11/001 ,  G06T2207/10024

Abstract: Techniques and constructs can determine an albedo map and a shading map from a digital image. The albedo and shading maps can be determined based at least in part on a color-difference threshold. A color shading map can be determined based at least in part on the albedo map, and lighting coefficients determined based on the color shading map. The digital image can be adjusted based at least in part on the lighting coefficients. In some examples, respective shading maps can be produced for individual color channels of the digital image. The color shading map can be produced based at least in part on the shading maps. In some examples, a plurality of regions of the digital image can be determined, as can proximity relationships between individual regions. The albedo shading maps can be determined based at least in part on the proximity relationships.

公开(公告)号：US20250030816A1

公开(公告)日：2025-01-23

申请号：US18710438

申请日：2022-11-10

Applicant: Microsoft Technology Licensing, LLC

Inventor： Jiaolong YANG ,  Yizhong Zhang ,  Xin TONG ,  Baining GUO

IPC: H04N7/15 ,  G06T5/50 ,  G06T7/55 ,  G06V40/16

Abstract: According to implementations of the subject matter described herein, there is provided a solution for an immersive video conference. In the solution, a conference mode for the video conference is determined at first, the conference mode indicating a layout of a virtual conference space for the video conference, and viewpoint information associated with the second participant in the video conference is determined based on the layout. Furthermore, a first view of the first participant is determined based on the viewpoint information and then sent to a conference device associated with the second participant to display a conference image to the second participant. Thereby, on the one hand, it is possible to enable the video conference participants to obtain a more authentic and immersive video conference experience, and on the other hand, to obtain a desired virtual conference space layout according to needs more flexibly.

公开(公告)号：US20230072701A1

公开(公告)日：2023-03-09

申请号：US17942776

申请日：2022-09-12

Applicant: Microsoft Technology Licensing, LLC

Inventor： Guojun Chen ,  Yue Dong ,  Xin TONG ,  Yingnan Ju ,  Pingchao Yu

IPC: G06T19/00 ,  G06F1/16 ,  G06F3/01

Abstract: Implementations of the subject matter described herein relate to mixed reality object rendering based on ambient light conditions. According to the embodiments of the subject matter described herein, while rendering an object a wearable computing device acquires light conditions of the real world, thereby increasing the reality of the rendered object. In particular, the wearable computing deice is configured to acquire an image of an environment where the wearable computing deice is located. The image is adjusted based on a cement parameter used w hen the image is captured. Subsequently, ambient light information is determined based on the adjusted image. In this way, the wearable computing deice can obtain more real and accurate emblem light information, so as to render to the user an object with enhanced reality. Accordingly, the user can have a better interaction experience.

公开(公告)号：US20240161382A1

公开(公告)日：2024-05-16

申请号：US18279717

申请日：2021-04-26

Applicant: Microsoft Technology Licensing, LLC

Inventor： Jongyoo KIM ,  Jiaolong YANG ,  Xin TONG

IPC: G06T15/04 ,  G06T7/40 ,  G06T7/70 ,  G06V10/54 ,  G06V20/70

CPC classification number: G06T15/04 ,  G06T7/40 ,  G06T7/70 ,  G06V10/54 ,  G06V20/70 ,  G06T2207/20081

Abstract: According to implementations of the present disclosure, there is provided a solution for completing textures of an object. In this solution, a complete texture map of an object is generated from a partial texture map of the object according to a texture generation model. A first prediction on whether a texture of at least one block in the complete texture map is an inferred texture is determined according to a texture discrimination model. A second image of the object is generated based on the complete texture map. A second prediction on whether the first image and the second image are generated images is determined according to an image discrimination model. The texture generation model, the texture and image discrimination models are trained based on the first and second predictions.

公开(公告)号：US20240135576A1

公开(公告)日：2024-04-25

申请号：US18274679

申请日：2022-02-08

Applicant: Microsoft Technology Licensing, LLC

Inventor： Zheng Zhang ,  Han Hu ,  Yue Cao ,  Xin TONG ,  Ze Liu

IPC: G06T7/73 ,  G06T7/62 ,  G06T7/90 ,  G06T17/00 ,  G06V10/44 ,  G06V20/64

CPC classification number: G06T7/73 ,  G06T7/62 ,  G06T7/90 ,  G06T17/00 ,  G06V10/44 ,  G06V20/64 ,  G06V2201/07

Abstract: According to implementations of the subject matter described herein, a solution is proposed for three-dimensional (3D) object detection. In this solution, feature representations of a plurality of points are extracted from point cloud data related to a 3D object. Initial feature representations of a set of candidate 3D objects are determined based on the feature representations of the plurality of points. Based on the feature representations of the plurality of points and the initial feature representations of the set of candidate 3D objects, a detection result for the 3D object is generated by determining self-correlations between the set of candidate 3D objects and cross-correlations between the plurality of points and the set of candidate 3D objects. In this way, without grouping points into candidate 3D objects, the 3D object in a 3D scene can be localized and recognized based on the self-correlations and cross-correlations.

公开(公告)号：US20190139248A1

公开(公告)日：2019-05-09

申请号：US16096448

申请日：2017-03-28

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Xin TONG ,  Yang LIU

IPC: G06T7/60 ,  G06N7/00 ,  G06N20/10 ,  G06T5/20 ,  G06T5/00 ,  G06T17/20

Abstract: In this disclosure, a solution for denoising a curve mesh is proposed. For a curve mesh including a polygonal facet, a noisy normal and a ground-truth normal of a first facet in the mesh is obtained. Then, based on the noisy normal, a first geometric feature of the first facet is determined from a plurality of neighboring facets of the first facet in the mesh. Next, based on the first geometric feature and the ground-truth normal, a mapping from the first geometric feature to the ground-truth normal of the first facet is determined for denoising the mesh.

公开(公告)号：US20210027526A1

公开(公告)日：2021-01-28

申请号：US17044270

申请日：2019-05-13

Applicant: Microsoft Technology Licensing, LLC

Inventor： Yue DONG ,  Guojun CHEN ,  Xin TONG

IPC: G06T15/60 ,  G06T15/80 ,  G06T17/20

Abstract: In accordance with implementations of the subject matter described herein, there is provided a solution of lighting estimation. In the solution, an input image about a real object and a depth map corresponding to the input image are obtained. A geometric structure of the scene in the input image is determined based on the depth map. Shading and shadow information on the real object caused by a light source in the scene is determined based on the determined geometric structure of the scene. Then, a lighting condition in the scene caused by the light source is determined based on the input image and the shading and shadow information. The virtual object rendered using the lighting condition obtained according to the solution can exhibit a realistic effect consistent with the real object.

公开(公告)号：US20200042863A1

公开(公告)日：2020-02-06

申请号：US16606653

申请日：2018-04-20

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Pengshuai WANG ,  Yang LIU ,  Xin TONG

IPC: G06N3/04 ,  G06F17/15 ,  G06F16/901 ,  G06F1/20

Abstract: The implementations of the subject matter described herein relate to an octree-based convolutional neural network. In some implementations, there is provided a computer-implemented method for processing a three-dimensional shape. The method comprises obtaining an octree for representing the three-dimensional shape. Nodes of the octree include empty nodes and non-empty nodes. The empty nodes exclude the three-dimensional shape and are leaf nodes of the octree, and the non-empty nodes include at least a part of the three-dimensional shape. The method further comprises for nodes in the octree with a depth associated with a convolutional layer of a convolutional neural network, performing a convolutional operation of the convolutional layer to obtain an output of the convolutional layer.