公开(公告)号：US20200226797A1

公开(公告)日：2020-07-16

申请号：US16249861

申请日：2019-01-16

Applicant: Disney Enterprises, Inc.

Inventor： Christopher Schroers ,  Erika Doggett ,  Stephan Marcel Mandt ,  Jared McPhillen ,  Scott Labrozzi ,  Romann Weber ,  Mauro Bamert

IPC: G06T9/20

Abstract: Systems and methods for predicting a target set of pixels are disclosed. In one embodiment, a method may include obtaining target content. The target content may include a target set of pixels to be predicted. The method may also include convolving the target set of pixels to generate an estimated set of pixels. The method may include matching a second set of pixels in the target content to the target set of pixels. The second set of pixels may be within a distance from the target set of pixels. The method may include refining the estimated set of pixels to generate a refined set of pixels using a second set of pixels in the target content.

公开(公告)号：US11335034B2

公开(公告)日：2022-05-17

申请号：US16249861

申请日：2019-01-16

Applicant: Disney Enterprises, Inc.

Inventor： Christopher Schroers ,  Erika Doggett ,  Stephan Marcel Mandt ,  Jared McPhillen ,  Scott Labrozzi ,  Romann Weber ,  Mauro Bamert

IPC: G06T9/20 ,  G06T9/00

Abstract: Systems and methods for predicting a target set of pixels are disclosed. In one embodiment, a method may include obtaining target content. The target content may include a target set of pixels to be predicted. The method may also include convolving the target set of pixels to generate an estimated set of pixels. The method may include matching a second set of pixels in the target content to the target set of pixels. The second set of pixels may be within a distance from the target set of pixels. The method may include refining the estimated set of pixels to generate a refined set of pixels using a second set of pixels in the target content.

公开(公告)号：US20190333190A1

公开(公告)日：2019-10-31

申请号：US16167388

申请日：2018-10-22

Applicant: Disney Enterprises, Inc.

Inventor： Christopher Schroers ,  Mauro Bamert ,  Erika Doggett ,  Jared McPhillen ,  Scott Labrozzi ,  Romann Weber

IPC: G06T5/00 ,  G06N3/08 ,  G06T5/20

Abstract: Systems and methods for distortion removal at multiple quality levels are disclosed. In one embodiment, a method may include receiving training content. The training content may include original content, reconstructed content, and training distortion quality levels corresponding to the reconstructed content. The reconstructed content may be derived from distorted original content. The method may also include training distortion quality levels corresponding to the reconstructed content. The method may further include receiving an initial distortion removal model. The method may include generating a conditioned distortion removal model by training the initial distortion removal model using the training content. The method may further include storing the conditioned distortion removal model.

公开(公告)号：US11983906B2

公开(公告)日：2024-05-14

申请号：US17704907

申请日：2022-03-25

Applicant: DISNEY ENTERPRISES, INC.

Inventor： Christopher Schroers ,  Erika Doggett ,  Stephan Mandt ,  Jared Mcphillen ,  Scott Labrozzi ,  Romann Weber ,  Mauro Bamert

IPC: G06T9/20 ,  G06T9/00

CPC classification number: G06T9/20 ,  G06T9/002

Abstract: Systems and methods for predicting a target set of pixels are disclosed. In one embodiment, a method may include obtaining target content. The target content may include a target set of pixels to be predicted. The method may also include convolving the target set of pixels to generate an estimated set of pixels. The method may include matching a second set of pixels in the target content to the target set of pixels. The second set of pixels may be within a distance from the target set of pixels. The method may include refining the estimated set of pixels to generate a refined set of pixels using a second set of pixels in the target content.

公开(公告)号：US10832383B2

公开(公告)日：2020-11-10

申请号：US16167388

申请日：2018-10-22

Applicant: Disney Enterprises, Inc.

Inventor： Christopher Schroers ,  Mauro Bamert ,  Erika Doggett ,  Jared McPhillen ,  Scott Labrozzi ,  Romann Weber

IPC: G06T5/20 ,  G06N3/08 ,  G06T5/00

Abstract: Systems and methods for distortion removal at multiple quality levels are disclosed. In one embodiment, a method may include receiving training content. The training content may include original content, reconstructed content, and training distortion quality levels corresponding to the reconstructed content. The reconstructed content may be derived from distorted original content. The method may also include training distortion quality levels corresponding to the reconstructed content. The method may further include receiving an initial distortion removal model. The method may include generating a conditioned distortion removal model by training the initial distortion removal model using the training content. The method may further include storing the conditioned distortion removal model.