专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2023057781A1 GENERATION OF A VIRTUAL VIEWPOINT IMAGE OF A PERSON FROM A SINGLE CAPTURED IMAGE 审中-公开
公开(公告)号：WO2023057781A1
公开(公告)日：2023-04-13
申请号：PCT/GR2021/000061
申请日：2021-10-08
申请人： FACEBOOK TECHNOLOGIES, LLC , SARAFIANOS, Nikolaos , TUNG, Tony
发明人： SARAFIANOS, Nikolaos , TUNG, Tony
IPC分类号： H04N13/268 , H04N13/261 , G06T7/11 , G06T7/194 , G06T15/04 , G06T15/20 , G06T15/205 , G06T2207/30196
摘要： In particular embodiments, to generate two videos corresponding to the two views of a human from the single video, multiple neural networks may be used to process a 2D video of a human in motion. Initially, a video of a person may be captured by a standard video camera. The video may comprise a plurality of frames including RGB images of the person. A computing system may process these images to generate the two videos corresponding to the two views of a human. As an example and not by way of limitation, an artificial reality headset may process these images to generate a mapping between the RGB pixels of each of the images to a 3D surface-based model of body part of the person. In order to generate the mapping, the artificial reality headset may use a mapping machine-learning model to process one of the RGB images to generate the mapping between pixels of the single RGB image to the 3D surface-based model of body part of the person.A machine-learning model may be used to refine the 3D surface-based model into a refined 3D surface- based model. The refined 3D surface-based model is then used to warp the single RGB image that was used to generate the 3D surface- based model to generate a texture of the person. The texture may then be used as an input to a full texture machine-learning model that generates a full-body UV texture from the partial texture generated by the warped RGB images. The full texture machine-learning model may be used to inpaint regions that are not seen or are self-occluded areas. As an example and not by way of limitation, if the partial texture generated by the warped RGB images have a partial texture of a person's hands, then the full texture machine-learning model may inpaint the region corresponding to the person's hands to generate a complete texture of the person's hands. After generating the full texture using the full texture machine-learning model, the artificial reality headset may then use a view generation machine- learning model to generate two different views of the person using the refined 3D surface-based model. That is, the view generation machine-learning model may generate a left eye refined 3D surface- based model and a right eye refined 3D surface-based model. The complete texture generated from the full texture machine-learning model may then be warped onto the left eye refined 3D surface-based model and the right eye refined 3D surface-based model. A neural Tenderer machine-learning model may then be applied to the warped left and right images to fill in missing pixel information to generate the stereo pair of images of the person. This method of generating a stereo pair of images and/or an image at a virtual viewpoint may be done without an explicit 3D reconstruction of the person.

2. 发明申请

WO2023057780A1 IMU-BASED DEAD RECKONING WITH LEARNED MOTION MODEL 审中-公开
公开(公告)号：WO2023057780A1
公开(公告)日：2023-04-13
申请号：PCT/GR2021/000060
申请日：2021-10-08
申请人： FACEBOOK TECHNOLOGIES, LLC , CARUSO, David , LIU, Wenxin , ILG, Florian Eddy Robert , DONG, Jing , MOURIKIS, Anastasios , ENGEL, Jakob Julian
发明人： CARUSO, David , LIU, Wenxin , ILG, Florian Eddy Robert , DONG, Jing , MOURIKIS, Anastasios , ENGEL, Jakob Julian
IPC分类号： G01C21/16
摘要： In one embodiment, a method includes, by a computing device, accessing current motion measurements associated with a current time instant, where the current motion measurements (104) are generated using a motion sensor (102), generating current gravity- aligned motion measurements based on the received current motion measurements (104), accessing a set of previous gravity-aligned motion measurements (112) associated with a time period prior to the current time instant, generating a probabilistic distribution (118) of the one or more displacements or the one or more speeds by using a statistical motion model (114) to process the current gravity- aligned motion measurements and the set of previous gravity-aligned motion measurements (112), and estimating, using a nonlinear state estimator (108), a state (120) of the motion sensor (102) based on the current motion measurements (104) and the probabilistic distribution (118) of the one or more displacements or the one or more speeds, the state including a three-dimensional position of the motion sensor (102) at the current time instant.

3. 发明申请

WO2022115255A1 METHODS FOR DEPTH SENSING USING CANDIDATE IMAGES SELECTED BASED ON AN EPIPOLAR LINE 审中-公开
公开(公告)号：WO2022115255A1
公开(公告)日：2022-06-02
申请号：PCT/US2021/059261
申请日：2021-11-12
申请人： FACEBOOK TECHNOLOGIES, LLC
发明人： HEGARTY, James Steven , LOVEGROVE, Steven John , KIM, Yongjun , CHHABRIA, Rajesh Lachhmandas , WANG, Zijian
IPC分类号： G06T7/521
摘要： A method for depth sensing from an image of a projected pattern is performed at an electronic device with one or more processors and memory. The method includes receiving an image of a projection of an illumination pattern; for a portion of the image, selecting a candidate image of a plurality of candidate images by comparing the portion of the image with a plurality of candidate images; and determining a depth for the portion of the image based on depth information associated with the selected candidate image. Related electronic devices and computer readable storage medium are also disclosed.

4. 发明申请

WO2022104277A2 CHEMICAL DIFFUSION TREATED VOLUME HOLOGRAMS AND METHODS FOR MAKING THE SAME 审中-公开
公开(公告)号：WO2022104277A2
公开(公告)日：2022-05-19
申请号：PCT/US2021/059548
申请日：2021-11-16
申请人： FACEBOOK TECHNOLOGIES, LLC
发明人： LANE, Austin , ALIM, Marvin Dion , YANG, Yang , MCNEIL, Janee Ashley
IPC分类号： G02B5/32 , G02B27/01 , G03H1/02 , G03H1/18 , G02B27/0172 , G02B5/1857 , G03H1/0248 , G03H1/181 , G03H1/182
摘要： A method for making an optical grating having a non-uniform refractive index profile along a direction substantially perpendicular to a plane defined by the optical grating includes placing a layer of photopolymerization material (302) having a first surface and a second surface that is opposite to the first surface between a first material transfer layer (304) and a second material transfer layer (306) so that the first surface of the layer of photopolymerization material is in contact with the first material transfer layer and the second surface of the layer of photopolymerization material is in contact with the second material transfer layer to allow material transfer between the layer of photopolymerization material and the first and second material transfer layers by diffusion. The material diffused can be a photoinitiator or an unreacted monomer from the photopolymer, or a photoinhibitor or low or high index material from the transfer layer.

5. 发明申请

WO2022098524A1 SYSTEMS AND METHODS FOR GENERATING DEVICE-IDENTIFYING DIGITAL CONTENT ON SOCIAL MEDIA PLATFORMS 审中-公开
公开(公告)号：WO2022098524A1
公开(公告)日：2022-05-12
申请号：PCT/US2021/056390
申请日：2021-10-23
申请人： FACEBOOK TECHNOLOGIES, LLC
发明人： JACOBSON, Matthew F.
IPC分类号： H04N21/2743 , H04N21/472 , H04N21/4788 , H04N21/8352
摘要： A computer-implemented method for generating device-identifying digital content (214) on social media platforms may include (i) identifying digital content (214) created by a content-creation device (204) for display on a social media platform (206), (ii) modifying the digital content (214) to indicate that the digital content (214) was created by the content-creation device (204) such that, when the modified digital content (214) is displayed on the social media platform (206), the modified digital content (214) identifies the content-creation device (204) as the source of the digital content (214), and (iii) displaying, on the social media platform (206), the modified digital content (214) to enable users of the social media platform(206) to identify the content-creation device (204) as the source of the digital content (214). Various other methods, systems, and computer-readable media are also disclosed.

6. 发明申请

WO2022081755A1 PAPER-BASED CUSHION PACKAGE 审中-公开
公开(公告)号：WO2022081755A1
公开(公告)日：2022-04-21
申请号：PCT/US2021/054842
申请日：2021-10-13
申请人： FACEBOOK TECHNOLOGIES, LLC
发明人： PINCUS, Derek
IPC分类号： B32B3/28 , B32B7/05 , B32B27/32 , B32B29/00 , B32B29/06 , B32B38/06 , B65D81/05
摘要： An example disclosed article (100) may include a first layer (120) and a second layer (140), where the first layer (120) and the second layer (140) may be bonded together within a peripheral region (102), the first layer (120) and the second layer (140)may be spaced apart within a cushion portion, the peripheral region may extend at least partially around the cushion portion (110), and the first layer (120) may include cellulose fibers. The article may be used as a component of a packaging arrangement that may be entirely recycled using a paper recycling process. Examples also include, for example, related methods, systems, and assemblies.

7. 发明申请

WO2022081238A1 COORDINATING COMMUNICATION LINKS FOR ARTIFICIAL REALITY 审中-公开
公开(公告)号：WO2022081238A1
公开(公告)日：2022-04-21
申请号：PCT/US2021/045018
申请日：2021-08-06
申请人： FACEBOOK TECHNOLOGIES, LLC
发明人： SHUKLA, Amit , ZHENG, Dong , LU, Gang
IPC分类号： H04W52/02 , H04B1/10
摘要： Disclosed herein are related to coordinating communication among a first access point, a first station device, a second access point, and a second station device. In one aspect, the second access point receives, from the first access point, a first beacon of the first access point at a first beacon transmission time. The first beacon may indicate an offset between the first beacon transmission time of the first beacon and a first data transmission time of the first access point for communication between the first access point and a first station device. In one aspect, the second access point may determine, according to the offset, a second data transmission time of the second access point to be distinct from the first data transmission time of the first access point. The second access point may communicate with a second station device, according to the second data transmission time.

8. 发明申请

WO2022076241A1 POLARIZATION SELECTIVE OPTICAL ELEMENT AND FABRICATION METHOD 审中-公开
公开(公告)号：WO2022076241A1
公开(公告)日：2022-04-14
申请号：PCT/US2021/052879
申请日：2021-09-30
申请人： FACEBOOK TECHNOLOGIES, LLC
发明人： SILVERSTEIN, Barry David , LU, Lu , LEE, Yun-Han , AMIRSOLAIMANI, Babak , WANG, Junren
IPC分类号： G02B5/30 , G02B5/32
摘要： A method includes obtaining a mixture including a first composition and a second composition. The method also includes forming a layer based on the mixture. Ratios between an amount of the first composition and an amount of the second composition at at least two locations of the layer are different.

9. 发明申请

WO2022076239A1 METHODS OF DRIVING LIGHT SOURCES IN A NEAR-EYE DISPLAY 审中-公开
公开(公告)号：WO2022076239A1
公开(公告)日：2022-04-14
申请号：PCT/US2021/052838
申请日：2021-09-30
申请人： FACEBOOK TECHNOLOGIES, LLC
发明人： CHOI, Min Hyuk , ZHUANG, Zhiming , CHOI, Wonjae , KIM, Cheonhong
IPC分类号： G06F3/147 , G06F3/01 , G09G3/32 , H04N13/332 , G09G3/3225
摘要： A method including determining a maximum luminance location of a display based on a field of view of an eye of a user of the display, and driving a plurality of light sources in the display based on locations of the plurality of light sources with respect to the maximum luminance location of the display. The plurality of light sources is controlled to have different luminance levels in different display zones corresponding to different zones on the retina of the eye of the user. In some examples, the display zones of the display system that have higher luminance levels can be dynamically changed based on the field of view or the gaze direction of the eye of the user.

10. 发明申请

WO2022072122A1 HIGH VOLTAGE OPTICAL TRANSFORMER INTEGRATION 审中-公开
公开(公告)号：WO2022072122A1
公开(公告)日：2022-04-07
申请号：PCT/US2021/049072
申请日：2021-09-03
申请人： FACEBOOK TECHNOLOGIES, LLC
发明人： PETERSON, Jonathan Robert , SCHELLER, Maik Andre , LIAO, Christopher Yuan Ting , OUDERKIRK, Andrew John , PIAZZA, Daniele , MENGUC, Yigit , LIU, Tianshu , LANDIG, Renate Eva Klementine
IPC分类号： H01L31/167 , H02M3/04
摘要： A high voltage-driven system includes a high voltage optical transformer and a high voltage driven device, where the high voltage optical transformer is located in close proximity to the high voltage driven device. A high voltage connection between the high voltage optical transformer and the high voltage driven device may be shorter than a low voltage connection between the high voltage optical transformer and a low voltage power source used to control the transformer.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式