公开(公告)号：WO2019075133A1

公开(公告)日：2019-04-18

申请号：PCT/US2018/055307

申请日：2018-10-10

Applicant: FYUSION, INC.

Inventor： HOLZER, Stefan Johannes Josef ,  RUSU, Radu Bogdan ,  MILLER, Stephen David ,  KALOGIROS, Pantelis ,  MUNARO, Matteo ,  TREVOR, Alexander Jay Bruen ,  BLODOW, Nico Gregor Sebastian ,  TAN, Luo Yi ,  PENZ, Mike ,  WAWRO, Martin Markus Hubert ,  RESO, Matthias ,  BEALL, Chris ,  TOMOTO, Yusuke ,  CHANDE, Krunal Ketan

IPC: H04N5/272 ,  H04N5/262 ,  H04N21/218 ,  H04N21/414

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：WO2022098606A1

公开(公告)日：2022-05-12

申请号：PCT/US2021/057575

申请日：2021-11-01

Applicant: FYUSION, INC.

Inventor： BERTEL, Tobias ,  TOMOTO, Yusuke ,  CHANDE, Krunal Ketan ,  ORTIZ-CAYON, Rodrigo ,  HOLZER, Stefan Johannes Josef ,  RICHARDT, Christian

IPC: G06T15/20 ,  G06T15/04 ,  G06T7/70 ,  G06T7/11 ,  G06T7/194 ,  G06T17/20

Abstract: Novel images may be generated using an image generator implemented on a processor. The image generator may receive as input neural features selected from a neural texture atlas. The image generator may also receive as input one or more position guides identifying position information for a plurality of input image pixels. The novel images may be evaluated using an image discriminator to determine a plurality of optimization values by comparing each of the plurality of novel images with a respective one of a corresponding plurality of input images. Each of the novel images may be generated from a respective camera pose relative to an object identical to that of the respective one of the corresponding plurality of input images. The image generator and the neural features may be updated based on the optimization values and stored on a storage device.