公开(公告)号：US11907839B2

公开(公告)日：2024-02-20

申请号：US17468511

申请日：2021-09-07

申请人： Adobe Inc.

发明人： Ratheesh Kalarot ,  Kevin Wampler ,  Jingwan Lu ,  Jakub Fiser ,  Elya Shechtman ,  Aliakbar Darabi ,  Alexandru Vasile Costin

IPC分类号： G06N3/08 ,  G06F3/04845 ,  G06T11/60 ,  G06T3/40 ,  G06T3/00 ,  G06F3/04847 ,  G06N20/20 ,  G06T5/00 ,  G06T5/20 ,  G06T11/00 ,  G06F18/40 ,  G06F18/211 ,  G06F18/214 ,  G06F18/21 ,  G06N3/045

CPC分类号： G06N3/08 ,  G06F3/04845 ,  G06F3/04847 ,  G06F18/211 ,  G06F18/214 ,  G06F18/2163 ,  G06F18/40 ,  G06N3/045 ,  G06N20/20 ,  G06T3/0006 ,  G06T3/0093 ,  G06T3/40 ,  G06T3/4038 ,  G06T3/4046 ,  G06T5/005 ,  G06T5/20 ,  G06T11/001 ,  G06T11/60 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20221 ,  G06T2210/22

摘要： Systems and methods combine an input image with an edited image generated using a generator neural network to preserve detail from the original image. A computing system provides an input image to a machine learning model to generate a latent space representation of the input image. The system provides the latent space representation to a generator neural network to generate a generated image. The system generates multiple scale representations of the input image, as well as multiple scale representations of the generated image. The system generates a first combined image based on first scale representations of the images and a first value. The system generates a second combined image based on second scale representations of the images and a second value. The system blends the first combined image with the second combined image to generate an output image.

公开(公告)号：US20240037922A1

公开(公告)日：2024-02-01

申请号：US17815451

申请日：2022-07-27

申请人： Adobe Inc.

发明人： Yijun Li ,  Nicholas Kolkin ,  Jingwan Lu ,  Elya Shechtman

IPC分类号： G06V10/82 ,  G06V10/77 ,  G06V10/46

CPC分类号： G06V10/82 ,  G06V10/7715 ,  G06V10/469

摘要： The present disclosure relates to systems, non-transitory computer-readable media, and methods for adapting generative neural networks to target domains utilizing an image translation neural network. In particular, in one or more embodiments, the disclosed systems utilize an image translation neural network to translate target results to a source domain for input in target neural network adaptation. For instance, in some embodiments, the disclosed systems compare a translated target result with a source result from a pretrained source generative neural network to adjust parameters of a target generative neural network to produce results corresponding in features to source results and corresponding in style to the target domain.

公开(公告)号：US11875221B2

公开(公告)日：2024-01-16

申请号：US17468476

申请日：2021-09-07

申请人： Adobe Inc.

发明人： Wei-An Lin ,  Baldo Faieta ,  Cameron Smith ,  Elya Shechtman ,  Jingwan Lu ,  Jun-Yan Zhu ,  Niloy Mitra ,  Ratheesh Kalarot ,  Richard Zhang ,  Shabnam Ghadar ,  Zhixin Shu

IPC分类号： G06N3/08 ,  G06F3/04845 ,  G06F3/04847 ,  G06T11/60 ,  G06T3/40 ,  G06N20/20 ,  G06T5/00 ,  G06T5/20 ,  G06T3/00 ,  G06T11/00 ,  G06F18/40 ,  G06F18/211 ,  G06F18/214 ,  G06F18/21 ,  G06N3/045

CPC分类号： G06N3/08 ,  G06F3/04845 ,  G06F3/04847 ,  G06F18/211 ,  G06F18/214 ,  G06F18/2163 ,  G06F18/40 ,  G06N3/045 ,  G06N20/20 ,  G06T3/0006 ,  G06T3/0093 ,  G06T3/40 ,  G06T3/4038 ,  G06T3/4046 ,  G06T5/005 ,  G06T5/20 ,  G06T11/001 ,  G06T11/60 ,  G06T2207/10024 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20221 ,  G06T2210/22

摘要： Systems and methods generate a filtering function for editing an image with reduced attribute correlation. An image editing system groups training data into bins according to a distribution of a target attribute. For each bin, the system samples a subset of the training data based on a pre-determined target distribution of a set of additional attributes in the training data. The system identifies a direction in the sampled training data corresponding to the distribution of the target attribute to generate a filtering vector for modifying the target attribute in an input image, obtains a latent space representation of an input image, applies the filtering vector to the latent space representation of the input image to generate a filtered latent space representation of the input image, and provides the filtered latent space representation as input to a neural network to generate an output image with a modification to the target attribute.

公开(公告)号：US20230360180A1

公开(公告)日：2023-11-09

申请号：US17661985

申请日：2022-05-04

申请人： Adobe Inc.

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

IPC分类号： G06V10/40 ,  G06T3/40 ,  G06T5/00

CPC分类号： G06T5/005 ,  G06T3/4046 ,  G06V10/40 ,  G06T2207/20084

摘要： 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：US20230342884A1

公开(公告)日：2023-10-26

申请号：US17725818

申请日：2022-04-21

申请人： Adobe Inc.

发明人： Krishna Kumar Singh ,  Yuheng Li ,  Yijun Li ,  Jingwan Lu ,  Elya Shechtman

IPC分类号： G06T5/00 ,  G06V10/82 ,  G06V10/74 ,  G06N3/04

CPC分类号： G06T5/002 ,  G06V10/82 ,  G06V10/761 ,  G06N3/0454 ,  G06T2207/20081

摘要： An image inpainting system is described that receives an input image that includes a masked region. From the input image, the image inpainting system generates a synthesized image that depicts an object in the masked region by selecting a first code that represents a known factor characterizing a visual appearance of the object and a second code that represents an unknown factor characterizing the visual appearance of the object apart from the known factor in latent space. The input image, the first code, and the second code are provided as input to a generative adversarial network that is trained to generate the synthesized image using contrastive losses. Different synthesized images are generated from the same input image using different combinations of first and second codes, and the synthesized images are output for display.

公开(公告)号：US11776188B2

公开(公告)日：2023-10-03

申请号：US17887685

申请日：2022-08-15

申请人： Adobe Inc.

发明人： Dingzeyu Li ,  Yang Zhou ,  Jose Ignacio Echevarria Vallespi ,  Elya Shechtman

IPC分类号： G06T13/20 ,  G06T17/20 ,  G06T13/40

CPC分类号： G06T13/205 ,  G06T13/40 ,  G06T17/20

摘要： Embodiments of the present invention provide systems, methods, and computer storage media for generating an animation of a talking head from an input audio signal of speech and a representation (such as a static image) of a head to animate. Generally, a neural network can learn to predict a set of 3D facial landmarks that can be used to drive the animation. In some embodiments, the neural network can learn to detect different speaking styles in the input speech and account for the different speaking styles when predicting the 3D facial landmarks. Generally, template 3D facial landmarks can be identified or extracted from the input image or other representation of the head, and the template 3D facial landmarks can be used with successive windows of audio from the input speech to predict 3D facial landmarks and generate a corresponding animation with plausible 3D effects.

公开(公告)号：US20230298148A1

公开(公告)日：2023-09-21

申请号：US17655663

申请日：2022-03-21

申请人： Adobe Inc.

发明人： He Zhang ,  Jianming Zhang ,  Jose Ignacio Echevarria Vallespi ,  Kalyan Sunkavalli ,  Meredith Payne Stotzner ,  Yinglan Ma ,  Zhe Lin ,  Elya Shechtman ,  Frederick Mandia

IPC分类号： G06T5/50 ,  G06T7/194 ,  G06T7/90 ,  G06T11/00

CPC分类号： G06T5/50 ,  G06T7/194 ,  G06T7/90 ,  G06T11/001 ,  G06T2207/20084 ,  G06T2207/20212 ,  G06T2200/24 ,  G06T2207/20092 ,  G06T2207/20016 ,  G06T2207/20081 ,  G06T2207/30168

摘要： The present disclosure relates to systems, non-transitory computer-readable media, and methods that implement a dual-branched neural network architecture to harmonize composite images. For example, in one or more implementations, the transformer-based harmonization system uses a convolutional branch and a transformer branch to generate a harmonized composite image based on an input composite image and a corresponding segmentation mask. More particularly, the convolutional branch comprises a series of convolutional neural network layers followed by a style normalization layer to extract localized information from the input composite image. Further, the transformer branch comprises a series of transformer neural network layers to extract global information based on different resolutions of the input composite image. Utilizing a decoder, the transformer-based harmonization system combines the local information and the global information from the corresponding convolutional branch and transformer branch to generate a harmonized composite image.

公开(公告)号：US20230260175A1

公开(公告)日：2023-08-17

申请号：US17650957

申请日：2022-02-14

申请人： Adobe Inc.

发明人： Nadav Epstein ,  Alexei A. Efros ,  Taesung Park ,  Richard Zhang ,  Elya Shechtman

IPC分类号： G06T11/60 ,  G06T7/90

CPC分类号： G06T11/60 ,  G06T7/90 ,  G06T2207/20084 ,  G06T2207/20212

摘要： The present disclosure relates to systems, methods, and non-transitory computer readable media for generating digital images depicting photorealistic scenes utilizing a digital image collaging neural network. For example, the disclosed systems utilize a digital image collaging neural network having a particular architecture for disentangling generation of scene layouts and pixel colors for different regions of a digital image. In some cases, the disclosed systems break down the process of generating a collage digital into generating images representing different regions such as a background and a foreground to be collaged into a final result. For example, utilizing the digital image collaging neural network, the disclosed systems determine scene layouts and pixel colors for both foreground digital images and background digital images to ultimately collage the foreground and background together into a collage digital image depicting a real-world scene.

公开(公告)号：US20230214967A1

公开(公告)日：2023-07-06

申请号：US18089218

申请日：2022-12-27

申请人： Adobe Inc.

发明人： Yuqian Zhou ,  Elya Shechtman ,  Connelly Stuart Barnes ,  Sohrab Amirghodsi

IPC分类号： G06T5/00 ,  G06T5/50 ,  G06T3/00 ,  G06N3/08

CPC分类号： G06T5/005 ,  G06T5/50 ,  G06T3/0093 ,  G06N3/08 ,  G06T2207/10024 ,  G06T2207/20224 ,  G06T2207/20084 ,  G06T2207/20081 ,  G06T2207/20221

摘要： Various disclosed embodiments are directed to inpainting one or more portions of a target image based on merging (or selecting) one or more portions of a warped image with (or from) one or more portions of an inpainting candidate (e.g., via a learning model). This, among other functionality described herein, resolves the inaccuracies of existing image inpainting technologies.

公开(公告)号：US20230162407A1

公开(公告)日：2023-05-25

申请号：US17455796

申请日：2021-11-19

申请人： ADOBE INC.

发明人： Ratheesh Kalarot ,  Timothy M. Converse ,  Shabnam Ghadar ,  John Thomas Nack ,  Jingwan Lu ,  Elya Shechtman ,  Baldo Faieta ,  Akhilesh Kumar

IPC分类号： G06T11/00 ,  G06K9/00 ,  G06N3/08

CPC分类号： G06T11/00 ,  G06K9/00288 ,  G06K9/00268 ,  G06N3/08

摘要： The present disclosure describes systems and methods for image processing. Embodiments of the present disclosure include an image processing apparatus configured to generate modified images (e.g., synthetic faces) by conditionally changing attributes or landmarks of an input image. A machine learning model of the image processing apparatus encodes the input image to obtain a joint conditional vector that represents attributes and landmarks of the input image in a vector space. The joint conditional vector is then modified, according to the techniques described herein, to form a latent vector used to generate a modified image. In some cases, the machine learning model is trained using a generative adversarial network (GAN) with a normalization technique, followed by joint training of a landmark embedding and attribute embedding (e.g., to reduce inference time).