公开(公告)号：US12086965B2

公开(公告)日：2024-09-10

申请号：US17520361

申请日：2021-11-05

Applicant: Adobe Inc.

Inventor： Yunhan Zhao ,  Connelly Barnes ,  Yuqian Zhou ,  Sohrab Amirghodsi ,  Elya Shechtman

IPC: G06T5/77 ,  G06T3/18 ,  G06T3/4046 ,  G06T5/50 ,  G06T7/30 ,  G06T7/50 ,  G06T7/90

CPC classification number: G06T5/77 ,  G06T3/18 ,  G06T3/4046 ,  G06T5/50 ,  G06T7/30 ,  G06T7/50 ,  G06T7/90 ,  G06T2207/20084 ,  G06T2207/20221

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for accurately restoring missing pixels within a hole region of a target image utilizing multi-image inpainting techniques based on incorporating geometric depth information. For example, in various implementations, the disclosed systems utilize a depth prediction of a source image as well as camera relative pose parameters. Additionally, in some implementations, the disclosed systems jointly optimize the depth rescaling and camera pose parameters before generating the reprojected image to further increase the accuracy of the reprojected image. Further, in various implementations, the disclosed systems utilize the reprojected image in connection with a content-aware fill model to generate a refined composite image that includes the target image having a hole, where the hole is filled in based on the reprojected image of the source image.

公开(公告)号：US20230145498A1

公开(公告)日：2023-05-11

申请号：US17520361

申请日：2021-11-05

Applicant: Adobe Inc.

Inventor： Yunhan Zhao ,  Connelly Barnes ,  Yuqian Zhou ,  Sohrab Amirghodsi ,  Elya Shechtman

IPC: G06T5/00 ,  G06T7/50 ,  G06T3/00 ,  G06T7/30 ,  G06T3/40 ,  G06T7/90 ,  G06T5/50

CPC classification number: G06T5/005 ,  G06T3/0093 ,  G06T3/4046 ,  G06T5/50 ,  G06T7/30 ,  G06T7/50 ,  G06T7/90 ,  G06T2207/20084 ,  G06T2207/20221

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media for accurately restoring missing pixels within a hole region of a target image utilizing multi-image inpainting techniques based on incorporating geometric depth information. For example, in various implementations, the disclosed systems utilize a depth prediction of a source image as well as camera relative pose parameters. Additionally, in some implementations, the disclosed systems jointly optimize the depth rescaling and camera pose parameters before generating the reprojected image to further increase the accuracy of the reprojected image. Further, in various implementations, the disclosed systems utilize the reprojected image in connection with a content-aware fill model to generate a refined composite image that includes the target image having a hole, where the hole is filled in based on the reprojected image of the source image.