公开(公告)号：US11967049B2

公开(公告)日：2024-04-23

申请号：US17531640

申请日：2021-11-19

Applicant: Adobe Inc.

Inventor： Stefano Petrangeli ,  Viswanathan Swaminathan ,  Haoliang Wang ,  YoungJoong Kwon

IPC: G06T5/00 ,  G06N3/045 ,  G06V10/75

CPC classification number: G06T5/005 ,  G06N3/045 ,  G06V10/7553

Abstract: The present disclosure describes multi-stage image editing techniques to improve detail and accuracy in edited images. An input image including a target region to be edited and an edit parameter specifying a modification to the target region are received. A parsing map of the input image is generated. A latent representation of the parsing map is generated. An edit is applied to the latent representation of the parsing map based on the edit parameter. The edited latent representation is input to a neural network to generate a modified parsing map including the target region with a shape change according to the edit parameter. Based on the input image and the modified parsing map, a masked image corresponding to the shape change is generated. Based on the masked image, a neural network is used to generate an edited image with the modification to the target region.

公开(公告)号：US20230162330A1

公开(公告)日：2023-05-25

申请号：US17531640

申请日：2021-11-19

Applicant: Adobe Inc.

Inventor： Stefano Petrangeli ,  Viswanathan Swaminathan ,  Haoliang Wang ,  YoungJoong Kwon

IPC: G06T5/00 ,  G06N3/04 ,  G06K9/62

CPC classification number: G06T5/005 ,  G06N3/0454 ,  G06K9/6209

Abstract: The present disclosure describes multi-stage image editing techniques to improve detail and accuracy in edited images. An input image including a target region to be edited and an edit parameter specifying a modification to the target region are received. A parsing map of the input image is generated. A latent representation of the parsing map is generated. An edit is applied to the latent representation of the parsing map based on the edit parameter. The edited latent representation is input to a neural network to generate a modified parsing map including the target region with a shape change according to the edit parameter. Based on the input image and the modified parsing map, a masked image corresponding to the shape change is generated. Based on the masked image, a neural network is used to generate an edited image with the modification to the target region.

公开(公告)号：US12051175B2

公开(公告)日：2024-07-30

申请号：US17097600

申请日：2020-11-13

Applicant: ADOBE INC.

Inventor： Stefano Petrangeli ,  Viswanathan Swaminathan ,  Haoliang Wang ,  YoungJoong Kwon

IPC: G06N3/08 ,  G06N3/045 ,  G06T3/604 ,  G06T3/606

CPC classification number: G06T3/604 ,  G06N3/045 ,  G06N3/08 ,  G06T3/606 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Methods, system, and computer storage media are provided for novel view synthesis. An input image depicting an object is received and utilized to generate, via a neural network, a target view image. In exemplary aspects, additional view images are also generated within the same pass of the neural network. A loss is determined based on the target view image and additional view images and is used to modify the neural network to reduce errors. In some aspects, a rotated view image is generated by warping a ground truth image from an initial angle to a rotated view angle that matches a view angle of an image synthesized via the neural network, such as a target view image. The rotated view image and the synthesized image matching the rotated view angle (e.g., a target view image) are utilized to compute a rotational loss.

公开(公告)号：US20220156886A1

公开(公告)日：2022-05-19

申请号：US17097600

申请日：2020-11-13

Applicant: ADOBE INC.

Inventor： Stefano Petrangeli ,  Viswanathan Swaminathan ,  Haoliang Wang ,  YoungJoong Kwon

IPC: G06T3/60 ,  G06N3/08 ,  G06N3/04

Abstract: Methods, system, and computer storage media are provided for novel view synthesis. An input image depicting an object is received and utilized to generate, via a neural network, a target view image. In exemplary aspects, additional view images are also generated within the same pass of the neural network. A loss is determined based on the target view image and additional view images and is used to modify the neural network to reduce errors. In some aspects, a rotated view image is generated by warping a ground truth image from an initial angle to a rotated view angle that matches a view angle of an image synthesized via the neural network, such as a target view image. The rotated view image and the synthesized image matching the rotated view angle (e.g., a target view image) are utilized to compute a rotational loss.