专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

41. 发明申请

US20170359570A1 Multi-View Interactive Digital Media Representation Lock Screen 审中-公开
公开(公告)号：US20170359570A1
公开(公告)日：2017-12-14
申请号：US15673125
申请日：2017-08-09
申请人： Fyusion, Inc.
发明人： Stefan Johannes Josef HOLZER , George Haber , Radu Bogdan Rusu , Vladimir Glavtchev , Mike Penz , Gabriel Popa
IPC分类号： H04N13/04 , H04N13/02 , G06F21/36
摘要： Various embodiments describe systems and processes for capturing and generating multi-view interactive digital media representations for display on a user device. In one aspect, a mobile device is provided which comprises a display, one or more processors, memory, and one or more programs stored in the memory. The one or more programs comprise instructions for locking the mobile device, and providing a lock screen on the display in a lock mode upon receiving user input for accessing the mobile device. The lock screen may display a multi-view interactive digital media representation (MIDMR) which provides an interactive three-dimensional representation of an object that is responsive to user interaction with the mobile device. The MIDMR may respond to spatial and movement sensors in the mobile device. The mobile device may be unlocked for use upon receiving user identification input, which may include maneuvering the MIDMR in a predetermined pattern.

42. 发明申请

US20170148199A1 SYSTEM AND METHOD FOR INFINITE SYNTHETIC IMAGE GENERATION FROM MULTI-DIRECTIONAL STRUCTURED IMAGE ARRAY 审中-公开
公开(公告)号：US20170148199A1
公开(公告)日：2017-05-25
申请号：US15425988
申请日：2017-02-06
申请人： Fyusion, Inc.
发明人： Stefan Johannes Josef Holzer , Radu Bogdan Rusu , Yuheng Ren
IPC分类号： G06T11/60 , G06T7/246 , G06T5/50
CPC分类号： G06T15/205 , G06F3/04845 , G06F17/30256 , G06F17/30277 , G06F17/30784 , G06F17/30837 , G06T3/4038 , G06T7/337 , G06T2207/10016 , G06T2207/10052 , G06T2207/20221 , H04N5/23238 , H04N5/265 , H04N13/279 , H04N13/282
摘要： This present disclosure relates to systems and processes for interpolating images of an object from a multi-directional structured image array. In particular embodiments, a plurality of images corresponding to a light field is obtained using a camera. Each image contains at least a portion of overlapping subject matter with another image. First, second, and third images are determined, which are the closest three images in the plurality of images to a desired image location in the light field. A first set of candidate transformations is identified between the first and second images, and a second set of candidate transformations is identified between the first and third images. For each pixel location in the desired image location, first and second best pixel values are calculated using the first and second set of candidate transformations, respectively, and the first and second best pixel values are blended to form an interpolated pixel.

43. 发明申请

US20170018055A1 ARTIFICIALLY RENDERING IMAGES USING VIEWPOINT INTERPOLATION AND EXTRAPOLATION 审中-公开
标题翻译：使用视点插值和扩展进行人工渲染图像
公开(公告)号：US20170018055A1
公开(公告)日：2017-01-19
申请号：US14800642
申请日：2015-07-15
申请人： Fyusion, Inc.
发明人： Stefan Johannes Josef Holzer , Stephen David Miller , Martin Saelzle , Radu Bogdan Rusu
IPC分类号： G06T3/00 , G06T11/60 , G06T7/20 , G06T7/00
CPC分类号： G06T11/60 , G06T15/205 , H04N13/111
摘要： Various embodiments of the present invention relate generally to systems and methods for artificially rendering images using viewpoint interpolation and extrapolation. According to particular embodiments, a method includes moving a set of control points perpendicular to a trajectory between a first frame and a second frame, where the first frame includes a first image captured from a first location and the second frame includes a second image captured from a second location. The set of control points is associated with a layer and each control point is moved based on an associated depth of the control point. The method also includes generating an artificially rendered image corresponding to a third location outside of the trajectory by extrapolating individual control points using the set of control points for the third location and extrapolating pixel locations using the individual control points.
摘要翻译：本发明的各种实施例一般涉及使用视点插值和外推人工渲染图像的系统和方法。根据特定实施例，一种方法包括移动垂直于第一帧和第二帧之间的轨迹的一组控制点，其中第一帧包括从第一位置捕获的第一图像，并且第二帧包括从第二个位置。该组控制点与一层相关联，并且每个控制点基于控制点的相关深度移动。所述方法还包括通过使用所述第三位置的控制点的集合外推外部控制点并使用各个控制点来外推像素位置，来生成对应于轨迹外的第三位置的人为渲染图像。

44. 发明申请

US20170017353A1 CUSTOMIZING THE VISUAL AND FUNCTIONAL EXPERIENCE OF AN APPLICATION 审中-公开
标题翻译：自定义应用程序的视觉和功能体验
公开(公告)号：US20170017353A1
公开(公告)日：2017-01-19
申请号：US14798872
申请日：2015-07-14
申请人： Fyusion, Inc.
发明人： Stefan Johannes Josef Holzer , Michelle Ho , Pantelis Kalogiros , Radu Bogdan Rusu
IPC分类号： G06F3/0482 , G06F3/0484
摘要： Various examples of the present disclosure include techniques and mechanisms for providing a customizable visual and functional experience for a user of an application or service. According to various examples, a system includes a first visual interface that is mapped to a first feature set to operate together as a first user interface that is presented throughout the application or service when selected. The system further includes a second visual interface that is mapped to a second feature set to operate together as a second user interface that is presented throughout the application or service when selected. The first feature set and second feature set differ from each other and both the first user interface and second user interface are customizable.
摘要翻译：本公开的各种示例包括用于为应用或服务的用户提供可定制的视觉和功能体验的技术和机制。根据各种示例，系统包括被映射到第一特征集合以一起操作为在选择时在整个应用或服务中呈现的第一用户界面的第一可视界面。该系统还包括第二可视界面，其被映射到第二特征集合以一起操作为在选择时在整个应用或服务中呈现的第二用户界面。第一功能集和第二功能集彼此不同，第一用户界面和第二用户界面都是可定制的。

45. 发明公开

US20240221402A1 METHOD AND APPARATUS FOR 3-D AUTO TAGGING 审中-公开
公开(公告)号：US20240221402A1
公开(公告)日：2024-07-04
申请号：US18607516
申请日：2024-03-17
申请人： Fyusion, Inc.
发明人： Chris Beall , Abhishek Kar , Stefan Johannes Josef Holzer , Radu Bogdan Rusu , Pavel Hanchar
IPC分类号： G06V20/70 , G06T17/30 , G06T19/00 , G06V10/422 , G06V10/772 , G06V20/10 , G06V20/20 , G06V20/64
CPC分类号： G06V20/70 , G06T17/30 , G06T19/003 , G06V10/422 , G06V10/772 , G06V20/10 , G06V20/20 , G06V20/64
摘要： A multi-view interactive digital media representation (MVIDMR) of an object can be generated from live images of an object captured from a camera. Selectable tags can be placed at locations on the object in the MVIDMR. When the selectable tags are selected, media content can be output which shows details of the object at location where the selectable tag is placed. A machine learning algorithm can be used to automatically recognize landmarks on the object in the frames of the MVIDMR and a structure from motion calculation can be used to determine 3-D positions associated with the landmarks. A 3-D skeleton associated with the object can be assembled from the 3-D positions and projected into the frames associated with the MVIDMR. The 3-D skeleton can be used to determine the selectable tag locations in the frames of the MVIDMR of the object.

46. 发明授权

US11989822B2 Damage detection from multi-view visual data 有权
公开(公告)号：US11989822B2
公开(公告)日：2024-05-21
申请号：US18338240
申请日：2023-06-20
申请人： Fyusion, Inc.
发明人： Stefan Johannes Josef Holzer , Abhishek Kar , Matteo Munaro , Pavel Hanchar , Radu Bogdan Rusu , Santi Arano
IPC分类号： G06T7/70 , G01C21/32 , G06F9/451 , G06F16/29 , G06F17/18 , G06F30/15 , G06N3/02 , G06Q30/02 , G06T7/00 , G06T7/593 , G06T15/10 , G06T15/20 , G06T17/00 , G06T19/00 , H04N13/243 , H04N13/271 , H04N23/63 , H04N13/00
CPC分类号： G06T15/205 , G01C21/32 , G06F9/453 , G06F16/29 , G06F17/18 , G06F30/15 , G06N3/02 , G06Q30/0278 , G06T7/0002 , G06T7/0004 , G06T7/593 , G06T7/70 , G06T15/10 , G06T17/00 , G06T19/003 , G06T19/006 , H04N13/243 , H04N13/271 , H04N23/633 , G06T2200/08 , G06T2200/24 , G06T2207/10016 , G06T2207/10028 , G06T2207/20076 , G06T2207/20081 , G06T2207/20084 , G06T2207/20224 , G06T2207/30108 , G06T2207/30244 , G06T2207/30248 , H04N2013/0081
摘要： A plurality of images may be analyzed to determine an object model. The object model may have a plurality of components, and each of the images may correspond with one or more of the components. Component condition information may be determined for one or more of the components based on the images. The component condition information may indicate damage incurred by the object portion corresponding with the component.

47. 发明授权

US11956412B2 Drone based capture of multi-view interactive digital media 有权
公开(公告)号：US11956412B2
公开(公告)日：2024-04-09
申请号：US16813506
申请日：2020-03-09
申请人： Fyusion, Inc.
发明人： Stefan Johannes Josef Holzer , Stephen David Miller , Radu Bogdan Rusu
IPC分类号： H04N13/282 , B64C39/02 , G05D1/00 , G06F3/04815 , G06F3/0488 , G06F16/51 , G06T15/20 , G06T17/00 , G06V10/10 , G06V20/10 , G06V20/17 , G06V20/70 , H04N5/262 , H04N7/18 , H04N23/698 , B64U101/30
CPC分类号： H04N13/282 , B64C39/024 , G05D1/0094 , G05D1/0202 , G06F3/04815 , G06F3/0488 , G06F16/51 , G06T15/205 , G06T17/00 , G06V10/17 , G06V20/10 , G06V20/17 , G06V20/70 , H04N5/2624 , H04N7/185 , H04N23/698 , B64U2101/30 , B64U2201/10
摘要： Various embodiments of the present disclosure relate generally to systems and methods for drone-based systems and methods for capturing a multi-media representation of an entity. In some embodiments, the multi-media representation is digital, or multi-view, or interactive, and/or the combinations thereof. According to particular embodiments, a drone having a camera is controlled or operated to obtain a plurality of images having location information. The plurality of images, including at least a portion of overlapping subject matter, are fused to form multi-view interactive digital media representations.

48. 发明公开

US20230419438A1 EXTRACTION OF STANDARDIZED IMAGES FROM A SINGLE-VIEW OR MULTI-VIEW CAPTURE 审中-公开
公开(公告)号：US20230419438A1
公开(公告)日：2023-12-28
申请号：US18240773
申请日：2023-08-31
申请人： Fyusion, Inc.
发明人： Stefan Johannes Josef Holzer , Matteo Munaro , Martin Markus Hubert Wawro , Abhishek Kar , Paval Hanchar , Krunal Ketan Chande , Radu Bogdan Rusu
IPC分类号： G06T3/00 , G06T7/70
CPC分类号： G06T3/0037 , G06T7/70 , G06T2207/20044 , G06T2207/30248 , G06T2207/30244
摘要： According to various embodiments, component information may be identified for each input image of an object. The component information may indicate a portion of the input image in which a particular component of the object is depicted. A viewpoint may be determined for each input image that indicates a camera pose for the input image relative to the object. A three-dimensional skeleton of the object may be determined based on the viewpoints and the component information. A multi-view panel corresponding to the designated component of the object that is navigable in three dimensions and that the portions of the input images in which the designated component of the object is depicted may be stored on a storage device.

49. 发明公开

US20230410332A1 STRUCTURING VISUAL DATA 审中-公开
公开(公告)号：US20230410332A1
公开(公告)日：2023-12-21
申请号：US18457166
申请日：2023-08-28
申请人： Fyusion, Inc.
发明人： Stefan Johannes Josef Holzer , Matteo Munaro , Radu Bogdan Rusu
IPC分类号： G06T7/38 , G06N3/04 , G06T19/00 , G06T17/20 , G06T7/33 , G06T7/00 , G06T15/20 , H04N23/60
CPC分类号： G06T7/38 , G06N3/04 , G06T19/006 , G06T17/20 , G06T7/33 , G06T7/97 , G06T15/205 , H04N23/64 , G06T2219/004
摘要： Mappings are determined between viewpoints of an object and an object model representing the object. Each mapping identifies a location on the object model corresponding with a portion of the object captured in one of the viewpoints. Tags for the object model are created based on the mappings, where each tag links one of the viewpoints to one of the locations on the object model. A user interface that includes the object model and the tags is provided for presentation on a display screen in a user interface. One of the viewpoints is presented in the user interface when the corresponding tag is selected in the object model.

50. 发明公开

US20230394776A1 MODIFICATION OF MULTI-VIEW INTERACTIVE DIGITAL MEDIA REPRESENTATION 审中-公开
公开(公告)号：US20230394776A1
公开(公告)日：2023-12-07
申请号：US18453209
申请日：2023-08-21
申请人： Fyusion, Inc.
发明人： Stefan Johannes Josef HOLZER , Stephen David Miller , Pantelis Kalogiros , George Haber , Radu Bogdan Rusu
IPC分类号： G06T19/20 , H04N13/156 , H04N23/698
CPC分类号： G06T19/20 , H04N23/698 , H04N13/156
摘要： Provided are mechanisms and processes for inserting a visual element into a multi-view digital media representation (MVIDMR). In one example, a process includes analyzing an MVIDMR to determine if there is an appropriate location to insert a visual element. Once a location is found, the type of visual element appropriate for the location is determined, where the type of visual element includes either a three-dimensional object to be inserted in the MVIDMR or a two-dimensional image to be inserted as or projected onto a background or object in the MVIDMR. A visual element that is appropriate for the location is then retrieved and inserted into the MVIDMR, such that the visual element is integrated into the MVIDMR and navigable by a user.

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