公开(公告)号：US20240320872A1

公开(公告)日：2024-09-26

申请号：US18426763

申请日：2024-01-30

Applicant: ADOBE INC.

Inventor： Tobias Hinz ,  Venkata Naveen Kumar Yadav Marri ,  Midhun Harikumar ,  Ajinkya Gorakhnath Kale ,  Zhe Lin ,  Oliver Wang ,  Jingwan Lu

IPC: G06T11/00 ,  G06F40/284 ,  G06F40/40

CPC classification number: G06T11/00 ,  G06F40/284 ,  G06F40/40 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A method, apparatus, non-transitory computer readable medium, and system for image generation include obtaining a text embedding of a text prompt and an image embedding of an image prompt. Some embodiments map the text embedding into a joint embedding space to obtain a joint text embedding and map the image embedding into the joint embedding space to obtain a joint image embedding. Some embodiments generate a synthetic image based on the joint text embedding and the joint image embedding.

公开(公告)号：US20240135512A1

公开(公告)日：2024-04-25

申请号：US18190556

申请日：2023-03-27

Applicant: Adobe Inc.

Inventor： Krishna Kumar Singh ,  Yijun Li ,  Jingwan Lu ,  Duygu Ceylan Aksit ,  Yangtuanfeng Wang ,  Jimei Yang ,  Tobias Hinz ,  Qing Liu ,  Jianming Zhang ,  Zhe Lin

IPC: G06T5/00 ,  G06T7/11 ,  G06V10/82 ,  G06V40/10

CPC classification number: G06T5/005 ,  G06T7/11 ,  G06V10/82 ,  G06V40/10 ,  G06T2207/20021 ,  G06T2207/20084 ,  G06T2207/20212 ,  G06T2207/30196

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify digital images via scene-based editing using image understanding facilitated by artificial intelligence. For example, in one or more embodiments the disclosed systems utilize generative machine learning models to create modified digital images portraying human subjects. In particular, the disclosed systems generate modified digital images by performing infill modifications to complete a digital image or human inpainting for portions of a digital image that portrays a human. Moreover, in some embodiments, the disclosed systems perform reposing of subjects portrayed within a digital image to generate modified digital images. In addition, the disclosed systems in some embodiments perform facial expression transfer and facial expression animations to generate modified digital images or animations.

公开(公告)号：US20240135511A1

公开(公告)日：2024-04-25

申请号：US18190544

申请日：2023-03-27

Applicant: Adobe Inc.

Inventor： Krishna Kumar Singh ,  Yijun Li ,  Jingwan Lu ,  Duygu Ceylan Aksit ,  Yangtuanfeng Wang ,  Jimei Yang ,  Tobias Hinz ,  Qing Liu ,  Jianming Zhang ,  Zhe Lin

IPC: G06T5/00 ,  G06V10/25 ,  G06V10/44 ,  G06V10/82

CPC classification number: G06T5/005 ,  G06V10/25 ,  G06V10/44 ,  G06V10/82 ,  G06T2207/30196

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify digital images via scene-based editing using image understanding facilitated by artificial intelligence. For example, in one or more embodiments the disclosed systems utilize generative machine learning models to create modified digital images portraying human subjects. In particular, the disclosed systems generate modified digital images by performing infill modifications to complete a digital image or human inpainting for portions of a digital image that portrays a human. Moreover, in some embodiments, the disclosed systems perform reposing of subjects portrayed within a digital image to generate modified digital images. In addition, the disclosed systems in some embodiments perform facial expression transfer and facial expression animations to generate modified digital images or animations.

公开(公告)号：US20230342893A1

公开(公告)日：2023-10-26

申请号：US17660090

申请日：2022-04-21

Applicant: Adobe Inc.

Inventor： Tobias Hinz ,  Shabnam Ghadar ,  Richard Zhang ,  Ratheesh Kalarot ,  Jingwan Lu ,  Elya Shechtman

IPC: G06T5/50 ,  G06T11/60 ,  G06V10/82

CPC classification number: G06T5/50 ,  G06T11/60 ,  G06V10/82 ,  G06T2207/20221 ,  G06T2207/30201

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for combining digital images. In particular, in one or more embodiments, the disclosed systems combine latent codes of a source digital image and a target digital image utilizing a blending network to determine a combined latent encoding and generate a combined digital image from the combined latent encoding utilizing a generative neural network. In some embodiments, the disclosed systems determine an intersection face mask between the source digital image and the combined digital image utilizing a face segmentation network and combine the source digital image and the combined digital image utilizing the intersection face mask to generate a blended digital image.

公开(公告)号：US20240169622A1

公开(公告)日：2024-05-23

申请号：US18057851

申请日：2022-11-22

Applicant: ADOBE INC.

Inventor： Shaoan Xie ,  Zhifei Zhang ,  Zhe Lin ,  Tobias Hinz

IPC: G06T11/60 ,  G06T7/11 ,  G06T11/00

CPC classification number: G06T11/60 ,  G06T7/11 ,  G06T11/001 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Systems and methods for multi-modal image editing are provided. In one aspect, a system and method for multi-modal image editing includes identifying an image, a prompt identifying an element to be added to the image, and a mask indicating a first region of the image for depicting the element. The system then generates a partially noisy image map that includes noise in the first region and image features from the image in a second region outside the first region. A diffusion model generates a composite image map based on the partially noisy image map and the prompt. In some cases, the composite image map includes the target element in the first region that corresponds to the mask.