公开(公告)号：US12260557B2

公开(公告)日：2025-03-25

申请号：US17838995

申请日：2022-06-13

Applicant: ADOBE INC.

Inventor： Zijun Wei ,  Yilin Wang ,  Jianming Zhang ,  He Zhang

IPC: G06K9/00 ,  G06T7/11 ,  G06T7/136 ,  G06V10/46 ,  G06V10/764

Abstract: An image processing system generates an image mask from an image. The image is processed by an object detector to identify a region having an object, and the region is classified based on an object type of the object. A masking pipeline is selected from a number of masking pipelines based on the classification of the region. The region is processed using the masking pipeline to generate a region mask. An image mask for the image is generated using the region mask.

公开(公告)号：US20250054116A1

公开(公告)日：2025-02-13

申请号：US18929330

申请日：2024-10-28

Applicant: Adobe Inc.

Inventor： Haitian Zheng ,  Zhe Lin ,  Jingwan Lu ,  Scott Cohen ,  Elya Shechtman ,  Connelly Barnes ,  Jianming Zhang ,  Ning Xu ,  Sohrab Amirghodsi

IPC: G06T5/77 ,  G06T3/4046 ,  G06V10/40

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that generate inpainted digital images utilizing a cascaded modulation inpainting neural network. For example, the disclosed systems utilize a cascaded modulation inpainting neural network that includes cascaded modulation decoder layers. For example, in one or more decoder layers, the disclosed systems start with global code modulation that captures the global-range image structures followed by an additional modulation that refines the global predictions. Accordingly, in one or more implementations, the image inpainting system provides a mechanism to correct distorted local details. Furthermore, in one or more implementations, the image inpainting system leverages fast Fourier convolutions block within different resolution layers of the encoder architecture to expand the receptive field of the encoder and to allow the network encoder to better capture global structure.

公开(公告)号：US20250014201A1

公开(公告)日：2025-01-09

申请号：US18887334

申请日：2024-09-17

Applicant: Adobe Inc.

Inventor： Jianming Zhang

IPC: G06T7/593 ,  G06F17/11 ,  G06N20/00

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and/or implementing machine learning models utilizing compressed log scene measurement maps. For example, the disclosed system generates compressed log scene measurement maps by converting scene measurement maps to compressed log scene measurement maps by applying a logarithmic function. In particular, the disclosed system uses scene measurement distribution metrics from a digital image to determine a base for the logarithmic function. In this way, the compressed log scene measurement maps normalize ranges within a digital image and accurately differentiates between scene elements objects at a variety of depths. Moreover, for training, the disclosed system generates a predicted scene measurement map via a machine learning model and compares the predicted scene measurement map with a compressed log ground truth map. By doing so, the disclosed system trains the machine learning model to generate accurate compressed log depth maps.

公开(公告)号：US20240338869A1

公开(公告)日：2024-10-10

申请号：US18474536

申请日：2023-09-26

Applicant: ADOBE INC.

Inventor： Yuqian Zhou ,  Krishna Kumar Singh ,  Zhifei Zhang ,  Difan Liu ,  Zhe Lin ,  Jianming Zhang ,  Qing Liu ,  Jingwan Lu ,  Elya Shechtman ,  Sohrab Amirghodsi ,  Connelly Stuart Barnes

IPC: G06T11/60

CPC classification number: G06T11/60

Abstract: An image processing system obtains an input image (e.g., a user provided image, etc.) and a mask indicating an edit region of the image. A user selects an image editing mode for an image generation network from a plurality of image editing modes. The image generation network generates an output image using the input image, the mask, and the image editing mode.

公开(公告)号：US20240169500A1

公开(公告)日：2024-05-23

申请号：US18058027

申请日：2022-11-22

Applicant: ADOBE INC.

Inventor： Haitian Zheng ,  Zhe Lin ,  Jianming Zhang ,  Connelly Stuart Barnes ,  Elya Shechtman ,  Jingwan Lu ,  Qing Liu ,  Sohrab Amirghodsi ,  Yuqian Zhou ,  Scott Cohen

IPC: G06T5/00

CPC classification number: G06T5/005 ,  G06T5/003 ,  G06T2207/20081 ,  G06T2207/20104

Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure receive an image comprising a first region that includes content and a second region to be inpainted. Noise is then added to the image to obtain a noisy image, and a plurality of intermediate output images are generated based on the noisy image using a diffusion model trained using a perceptual loss. The intermediate output images predict a final output image based on a corresponding intermediate noise level of the diffusion model. The diffusion model then generates the final output image based on the intermediate output image. The final output image includes inpainted content in the second region that is consistent with the content in the first region.

公开(公告)号：US11983632B2

公开(公告)日：2024-05-14

申请号：US18309367

申请日：2023-04-28

Applicant: Adobe Inc.

Inventor： Shikun Liu ,  Zhe Lin ,  Yilin Wang ,  Jianming Zhang ,  Federico Perazzi

IPC: G06N3/082 ,  G06N3/04

CPC classification number: G06N3/082 ,  G06N3/04

Abstract: The disclosure describes one or more implementations of a neural network architecture pruning system that automatically and progressively prunes neural networks. For instance, the neural network architecture pruning system can automatically reduce the size of an untrained or previously-trained neural network without reducing the accuracy of the neural network. For example, the neural network architecture pruning system jointly trains portions of a neural network while progressively pruning redundant subsets of the neural network at each training iteration. In many instances, the neural network architecture pruning system increases the accuracy of the neural network by progressively removing excess or redundant portions (e.g., channels or layers) of the neural network. Further, by removing portions of a neural network, the neural network architecture pruning system can increase the efficiency of the neural network.

公开(公告)号：US20240135514A1

公开(公告)日：2024-04-25

申请号：US18460365

申请日：2023-09-01

Applicant: Adobe Inc.

Inventor： Daniil Pakhomov ,  Qing Liu ,  Zhihong Ding ,  Scott Cohen ,  Zhe Lin ,  Jianming Zhang ,  Zhifei Zhang ,  Ohiremen Dibua ,  Mariette Souppe ,  Krishna Kumar Singh ,  Jonathan Brandt

IPC: G06T5/00 ,  G06F3/04845 ,  G06T7/11 ,  G06T7/194 ,  G06T7/70

CPC classification number: G06T5/005 ,  G06F3/04845 ,  G06T5/002 ,  G06T7/11 ,  G06T7/194 ,  G06T7/70 ,  G06T2200/24 ,  G06T2207/20021 ,  G06T2207/20084 ,  G06T2207/20092

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify digital images via multi-layered scene completion techniques facilitated by artificial intelligence. For instance, in some embodiments, the disclosed systems receive a digital image portraying a first object and a second object against a background, where the first object occludes a portion of the second object. Additionally, the disclosed systems pre-process the digital image to generate a first content fill for the portion of the second object occluded by the first object and a second content fill for a portion of the background occluded by the second object. After pre-processing, the disclosed systems detect one or more user interactions to move or delete the first object from the digital image. The disclosed systems further modify the digital image by moving or deleting the first object and exposing the first content fill for the portion of the second object.

公开(公告)号：US20240127412A1

公开(公告)日：2024-04-18

申请号：US17937708

申请日：2022-10-03

Applicant: Adobe Inc.

Inventor： Zhe Lin ,  Haitian Zheng ,  Elya Shechtman ,  Jianming Zhang ,  Jingwan Lu ,  Ning Xu ,  Qing Liu ,  Scott Cohen ,  Sohrab Amirghodsi

IPC: G06T5/00 ,  G06T7/11

CPC classification number: G06T5/005 ,  G06T7/11 ,  G06T2207/20084 ,  G06T2207/20092

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for panoptically guiding digital image inpainting utilizing a panoptic inpainting neural network. In some embodiments, the disclosed systems utilize a panoptic inpainting neural network to generate an inpainted digital image according to panoptic segmentation map that defines pixel regions corresponding to different panoptic labels. In some cases, the disclosed systems train a neural network utilizing a semantic discriminator that facilitates generation of digital images that are realistic while also conforming to a semantic segmentation. The disclosed systems generate and provide a panoptic inpainting interface to facilitate user interaction for inpainting digital images. In certain embodiments, the disclosed systems iteratively update an inpainted digital image based on changes to a panoptic segmentation map.

公开(公告)号：US11868889B2

公开(公告)日：2024-01-09

申请号：US17588516

申请日：2022-01-31

Applicant: Adobe Inc.

Inventor： Zhe Lin ,  Xiaohui Shen ,  Mingyang Ling ,  Jianming Zhang ,  Jason Wen Yong Kuen

IPC: G06N3/08 ,  G06N3/04 ,  G06V20/20 ,  G06V20/64 ,  G06V10/82 ,  G06V20/10 ,  G06F18/214 ,  G06V10/764 ,  G06V10/44

CPC classification number: G06N3/08 ,  G06F18/214 ,  G06N3/04 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G06V20/10 ,  G06V20/20 ,  G06V20/64

Abstract: In implementations of object detection in images, object detectors are trained using heterogeneous training datasets. A first training dataset is used to train an image tagging network to determine an attention map of an input image for a target concept. A second training dataset is used to train a conditional detection network that accepts as conditional inputs the attention map and a word embedding of the target concept. Despite the conditional detection network being trained with a training dataset having a small number of seen classes (e.g., classes in a training dataset), it generalizes to novel, unseen classes by concept conditioning, since the target concept propagates through the conditional detection network via the conditional inputs, thus influencing classification and region proposal. Hence, classes of objects that can be detected are expanded, without the need to scale training databases to include additional classes.

公开(公告)号：US20230401716A1

公开(公告)日：2023-12-14

申请号：US17806312

申请日：2022-06-10

Applicant: ADOBE INC.

Inventor： Yilin Wang ,  Chenglin Yang ,  Jianming Zhang ,  He Zhang ,  Zijun Wei ,  Zhe Lin

IPC: G06T7/10 ,  G06T11/60 ,  G06N3/08

CPC classification number: G06T7/10 ,  G06T11/60 ,  G06N3/088

Abstract: Systems and methods for image segmentation are described. Embodiments of the present disclosure receive an image depicting an object; generate image features for the image by performing a convolutional self-attention operation that outputs a plurality of attention-weighted values for a convolutional kernel applied at a position of a sliding window on the image; and generate label data that identifies the object based on the image features.