-
公开(公告)号：US10861213B1
公开(公告)日：2020-12-08
申请号：US16726214
申请日：2019-12-23
Applicant: Fyusion, Inc.
Inventor： Stefan Johannes Josef Holzer , Matthias Reso , Pavel Hanchar , Radu Bogdan Rusu
Abstract: Systems and methods for automatic generation of artificial motion blur are provided. The method includes obtaining a sequence of images of an object captured along a camera translation. Then, a multi-view interactive digital media representation (MIDMR) of the object is generated. Generating the MIDMR includes segmenting the object and then adding a blur effect to all parts of the MIDMR except for the segmented object.
-
公开(公告)号：US20200234451A1
公开(公告)日：2020-07-23
申请号：US16518512
申请日：2019-07-22
Applicant: Fyusion, Inc.
Inventor： Stefan Johannes Josef Holzer , Matthias Reso , Abhishek Kar , Julius Santiago , Pavel Hanchar , Radu Bogdan Rusu
Abstract: A segmentation of an object depicted in a first visual representation may be determined. The segmentation may include for each image a first respective image portion that includes the object, a second respective image portion that includes a respective ground area located beneath the object, and a third respective image portion that includes a background area located above the second respective portion and behind the object. A second visual representation may be constructed that includes the first respective image portion and a target background image portion that replaces the third respective image portion and that is selected from a target background image based on an area of the third respective image portion relative to the respective image.
-
公开(公告)号：US10949978B2
公开(公告)日：2021-03-16
申请号：US16518512
申请日：2019-07-22
Applicant: Fyusion, Inc.
Inventor： Stefan Johannes Josef Holzer , Matthias Reso , Abhishek Kar , Julius Santiago , Pavel Hanchar , Radu Bogdan Rusu
Abstract: A segmentation of an object depicted in a first visual representation may be determined. The segmentation may include for each image a first respective image portion that includes the object, a second respective image portion that includes a respective ground area located beneath the object, and a third respective image portion that includes a background area located above the second respective portion and behind the object. A second visual representation may be constructed that includes the first respective image portion and a target background image portion that replaces the third respective image portion and that is selected from a target background image based on an area of the third respective image portion relative to the respective image.
-
公开(公告)号：US20200349757A1
公开(公告)日：2020-11-05
申请号：US16518585
申请日：2019-07-22
Applicant: Fyusion, Inc.
Inventor： Stefan Johannes Josef Holzer , Abhishek Kar , Matteo Munaro , Aidas Liaudanskas , Matthias Reso , Alexander Jay Bruen Trevor , Radu Bogdan Rusu
IPC: G06T15/20 , G06T17/20 , G06T7/50 , G06K9/00 , G06F3/0481
Abstract: Pixels in a visual representation of an object that includes one or more perspective view images may be mapped to a standard view of the object. Based on the mapping, a portion of the object captured in the visual representation of the object may be identified. A user interface on a display device may indicate the identified object portion.
-
公开(公告)号：US10469768B2
公开(公告)日：2019-11-05
申请号：US15936141
申请日：2018-03-26
Applicant: Fyusion, Inc.
Inventor： Stefan Johannes Josef Holzer , Radu Bogdan Rusu , Stephen David Miller , Pantelis Kalogiros , Matteo Munaro , Alexander Jay Bruen Trevor , Nico Gregor Sebastian Blodow , Luo Yi Tan , Mike Penz , Martin Markus Hubert Wawro , Matthias Reso , Chris Beall , Yusuke Tomoto , Krunal Ketan Chande
IPC: H04N5/272 , H04N5/265 , G06T19/00 , H04N13/111 , G06T13/40 , G06T7/11 , H04N13/282 , G06K9/00 , H04N5/232 , G06T7/194 , H04N13/279
Abstract: Various embodiments of the present invention relate generally to systems and methods for analyzing and manipulating images and video. In particular, a multi-view interactive digital media representation (MVIDMR) of a person can be generated from live images of a person captured from a hand-held camera. Using the image data from the live images, a skeleton of the person and a boundary between the person and a background can be determined from different viewing angles and across multiple images. Using the skeleton and the boundary data, effects can be added to the person, such as wings. The effects can change from image to image to account for the different viewing angles of the person captured in each image.
-
Patent Agency Ranking
公开(公告)号：US20190116322A1
公开(公告)日：2019-04-18
申请号：US15936131
申请日：2018-03-26
Applicant: Fyusion, Inc.
Inventor： Stefan Johannes Josef Holzer , Radu Bogdan Rusu , Stephen David Miller , Pantelis Kalogiros , Matteo Munaro , Alexander Jay Bruen Trevor , Nico Gregor Sebastian Blodow , Luo Yi Tan , Mike Penz , Martin Markus Hubert Wawro , Matthias Reso , Chris Beall , Yusuke Tomoto , Krunal Ketan Chande
CPC classification number: H04N5/272 , G06K9/00369 , G06K9/00671 , G06T7/11 , G06T7/194 , G06T13/40 , G06T19/006 , G06T2207/10016 , G06T2207/30196 , H04N5/23216 , H04N5/265 , H04N13/111 , H04N13/279 , H04N13/282 , H04N2005/2726
Abstract: Various embodiments of the present invention relate generally to systems and methods for analyzing and manipulating images and video. In particular, a multi-view interactive digital media representation (MVIDMR) of a person can be generated from live images of a person captured from a hand-held camera. Using the image data from the live images, a skeleton of the person and a boundary between the person and a background can be determined from different viewing angles and across multiple images. Using the skeleton and the boundary data, effects can be added to the person, such as wings. The effects can change from image to image to account for the different viewing angles of the person captured in each image.
-
公开(公告)号：US10950032B2
公开(公告)日：2021-03-16
申请号：US16518585
申请日：2019-07-22
Applicant: Fyusion, Inc.
Inventor： Stefan Johannes Josef Holzer , Abhishek Kar , Matteo Munaro , Aidas Liaudanskas , Matthias Reso , Alexander Jay Bruen Trevor , Radu Bogdan Rusu
IPC: G06T15/20 , G06T17/20 , G06K9/00 , G06F3/0481 , G06T7/50
Abstract: Pixels in a visual representation of an object that includes one or more perspective view images may be mapped to a standard view of the object. Based on the mapping, a portion of the object captured in the visual representation of the object may be identified. A user interface on a display device may indicate the identified object portion.
-
公开(公告)号：US10855936B2
公开(公告)日：2020-12-01
申请号：US16579572
申请日：2019-09-23
Applicant: Fyusion, Inc.
Inventor： Stefan Johannes Josef Holzer , Radu Bogdan Rusu , Stephen David Miller , Pantelis Kalogiros , Matteo Munaro , Alexander Jay Bruen Trevor , Nico Gregor Sebastian Blodow , Luo Yi Tan , Mike Penz , Martin Markus Hubert Wawro , Matthias Reso , Chris Beall , Yusuke Tomoto , Krunal Ketan Chande
IPC: H04N5/272 , G06T7/194 , G06T7/11 , H04N13/282 , G06K9/00 , G06T13/40 , H04N5/232 , H04N5/265 , H04N13/111 , G06T19/00 , H04N13/279
Abstract: Various embodiments of the present invention relate generally to systems and methods for analyzing and manipulating images and video. In particular, a multi-view interactive digital media representation (MVIDMR) of a person can be generated from live images of a person captured from a hand-held camera. Using the image data from the live images, a skeleton of the person and a boundary between the person and a background can be determined from different viewing angles and across multiple images. Using the skeleton and the boundary data, effects can be added to the person, such as wings. The effects can change from image to image to account for the different viewing angles of the person captured in each image.
-
公开(公告)号：US20200021752A1
公开(公告)日：2020-01-16
申请号：US16579572
申请日：2019-09-23
Applicant: Fyusion, Inc.
Inventor： Stefan Johannes Josef Holzer , Radu Bogdan Rusu , Stephen David Miller , Pantelis Kalogiros , Matteo Munaro , Alexander Jay Bruen Trevor , Nico Gregor Sebastian Blodow , Luo Yi Tan , Mike Penz , Martin Markus Hubert Wawro , Matthias Reso , Chris Beall , Yusuke Tomoto , Krunal Ketan Chande
IPC: H04N5/272 , G06T19/00 , H04N13/111 , H04N5/265 , H04N5/232 , G06T13/40 , G06K9/00 , H04N13/282 , G06T7/11 , G06T7/194
Abstract: Various embodiments of the present invention relate generally to systems and methods for analyzing and manipulating images and video. In particular, a multi-view interactive digital media representation (MVIDMR) of a person can be generated from live images of a person captured from a hand-held camera. Using the image data from the live images, a skeleton of the person and a boundary between the person and a background can be determined from different viewing angles and across multiple images. Using the skeleton and the boundary data, effects can be added to the person, such as wings. The effects can change from image to image to account for the different viewing angles of the person captured in each image.
-
公开(公告)号：US10356341B2
公开(公告)日：2019-07-16
申请号：US15936131
申请日：2018-03-26
Applicant: Fyusion, Inc.
Inventor： Stefan Johannes Josef Holzer , Radu Bogdan Rusu , Stephen David Miller , Pantelis Kalogiros , Matteo Munaro , Alexander Jay Bruen Trevor , Nico Gregor Sebastian Blodow , Luo Yi Tan , Mike Penz , Martin Markus Hubert Wawro , Matthias Reso , Chris Beall , Yusuke Tomoto , Krunal Ketan Chande
IPC: H04N13/282 , H04N13/279 , G06T7/11 , H04N5/272 , H04N5/265 , H04N5/232 , G06T7/194 , G06T13/40 , G06K9/00 , H04N13/111 , G06T19/00
Abstract: Various embodiments of the present invention relate generally to systems and methods for analyzing and manipulating images and video. In particular, a multi-view interactive digital media representation (MVIDMR) of a person can be generated from live images of a person captured from a hand-held camera. Using the image data from the live images, a skeleton of the person and a boundary between the person and a background can be determined from different viewing angles and across multiple images. Using the skeleton and the boundary data, effects can be added to the person, such as wings. The effects can change from image to image to account for the different viewing angles of the person captured in each image.
-
-
-
-
-
-
-
-
-
Search Results
11
records
(took 0.016 seconds)
