-
公开(公告)号：US11934958B2
公开(公告)日：2024-03-19
申请号：US17147912
申请日：2021-01-13
Applicant: Adobe Inc.
Inventor： Zhixin Shu , Zhe Lin , Yuchen Liu , Yijun Li
Abstract: This disclosure describes one or more embodiments of systems, non-transitory computer-readable media, and methods that utilize channel pruning and knowledge distillation to generate a compact noise-to-image GAN. For example, the disclosed systems prune less informative channels via outgoing channel weights of the GAN. In some implementations, the disclosed systems further utilize content-aware pruning by utilizing a differentiable loss between an image generated by the GAN and a modified version of the image to identify sensitive channels within the GAN during channel pruning. In some embodiments, the disclosed systems utilize knowledge distillation to learn parameters for the pruned GAN to mimic a full-size GAN. In certain implementations, the disclosed systems utilize content-aware knowledge distillation by applying content masks on images generated by both the pruned GAN and its full-size counterpart to obtain knowledge distillation losses between the images for use in learning the parameters for the pruned GAN.
-
公开(公告)号：US20240037922A1
公开(公告)日：2024-02-01
申请号：US17815451
申请日：2022-07-27
Applicant: Adobe Inc.
Inventor： Yijun Li , Nicholas Kolkin , Jingwan Lu , Elya Shechtman
CPC classification number: G06V10/82 , G06V10/7715 , G06V10/469
Abstract: 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：US11803950B2
公开(公告)日：2023-10-31
申请号：US17447893
申请日：2021-09-16
Applicant: Adobe Inc.
Inventor： Yijun Li , Ionut Mironic{hacek over (a)}
CPC classification number: G06T5/50 , G06N3/04 , G06T5/002 , G06T7/50 , G06T11/001 , G06T2200/24 , G06T2207/20081 , G06T2207/20084 , G06T2207/20221
Abstract: Techniques for generating style-transferred images are provided. In some embodiments, a content image, a style image, and a user input indicating one or more modifications that operate on style-transferred images are received. In some embodiments, an initial style-transferred image is generated using a machine learning model. In some examples, the initial style-transferred image comprises features associated with the style image applied to content included in the content image. In some embodiments, a modified style-transferred image is generated by modifying the initial style-transferred image based at least in part on the user input indicating the one or more modifications.
-
公开(公告)号：US20230342884A1
公开(公告)日：2023-10-26
申请号：US17725818
申请日：2022-04-21
Applicant: Adobe Inc.
Inventor： Krishna Kumar Singh , Yuheng Li , Yijun Li , Jingwan Lu , Elya Shechtman
CPC classification number: G06T5/002 , G06V10/82 , G06V10/761 , G06N3/0454 , G06T2207/20081
Abstract: 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：US20230140146A1
公开(公告)日：2023-05-04
申请号：US17519117
申请日：2021-11-04
Applicant: Adobe Inc.
Inventor： Daichi Ito , Yijun Li , Yannick Hold-Geoffroy , Koki Madono , Jose Ignacio Echevarria Vallespi , Cameron Younger Smith
Abstract: A vectorized caricature avatar generator receives a user image from which face parameters are generated. Segments of the user image including certain facial features (e.g., hair, facial hair, eyeglasses) are also identified. Segment parameter values are also determined, the segment parameter values being those parameter values from a set of caricature avatars that correspond to the segments of the user image. The face parameter values and the segment parameter values are used to generate a caricature avatar of the user in the user image.
-
Patent Agency Ranking
36.发明申请公开(公告)号：US20230053588A1
公开(公告)日：2023-02-23
申请号：US17400426
申请日：2021-08-12
Applicant: Adobe Inc.
Inventor： Yuheng Li , Yijun Li , Jingwan Lu , Elya Shechtman , Krishna Kumar Singh
Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that generate synthetized digital images via multi-resolution generator neural networks. The disclosed system extracts multi-resolution features from a scene representation to condition a spatial feature tensor and a latent code to modulate an output of a generator neural network. For example, the disclosed systems utilizes a base encoder of the generator neural network to generate a feature set from a semantic label map of a scene. The disclosed system then utilizes a bottom-up encoder to extract multi-resolution features and generate a latent code from the feature set. Furthermore, the disclosed system determines a spatial feature tensor by utilizing a top-down encoder to up-sample and aggregate the multi-resolution features. The disclosed system then utilizes a decoder to generate a synthesized digital image based on the spatial feature tensor and the latent code.
-
37.发明申请公开(公告)号：US20220261972A1
公开(公告)日：2022-08-18
申请号：US17178681
申请日：2021-02-18
Applicant: Adobe Inc.
Inventor： Pei Wang , Yijun Li , Jingwan Lu , Krishna Kumar Singh
Abstract: This disclosure describes methods, non-transitory computer readable storage media, and systems that utilize image-guided model inversion of an image classifier with a discriminator. The disclosed systems utilize a neural network image classifier to encode features of an initial image and a target image. The disclosed system also reduces a feature distance between the features of the initial image and the features of the target image at a plurality of layers of the neural network image classifier by utilizing a feature distance regularizer. Additionally, the disclosed system reduces a patch difference between image patches of the initial image and image patches of the target image by utilizing a patch-based discriminator with a patch consistency regularizer. The disclosed system then generates a synthesized digital image based on the constrained feature set and constrained image patches of the initial image.
-
公开(公告)号：US20220076374A1
公开(公告)日：2022-03-10
申请号：US17013332
申请日：2020-09-04
Applicant: Adobe Inc.
Inventor： Yijun Li , Richard Zhang , Jingwan Lu , Elya Schechtman
Abstract: One example method involves operations for receiving a request to transform an input image into a target image. Operations further include providing the input image to a machine learning model trained to adapt images. Training the machine learning model includes accessing training data having a source domain of images and a target domain of images with a target style. Training further includes using a pre-trained generative model to generate an adapted source domain of adapted images having the target style. The adapted source domain is generated by determining a rate of change for parameters of the target style, generating weighted parameters by applying a weight to each of the parameters based on their respective rate of change, and applying the weighted parameters to the source domain. Additionally, operations include using the machine learning model to generate the target image by modifying parameters of the input image using the target style.
-
公开(公告)号：US12260530B2
公开(公告)日：2025-03-25
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
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.
-
40.发明申请公开(公告)号：US20250078327A1
公开(公告)日：2025-03-06
申请号：US18457895
申请日：2023-08-29
Applicant: Adobe Inc.
Inventor： Zhipeng Bao , Yijun Li , Krishna Kumar Singh
Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that utilize a text-image alignment loss to train a diffusion model to generate digital images from input text. In particular, in some embodiments, the disclosed systems generate a prompt noise representation form a text prompt with a first text concept and a second text concept using a denoising step of a diffusion neural network. Further, in some embodiments, the disclosed systems generate a first concept noise representation from the first text concept and a second concept noise representation from the second text concept. Moreover, the disclosed systems combine the first and second concept noise representation to generate a combined concept noise representation. Accordingly, in some embodiments, by comparing the combined concept noise representation and the prompt noise representation, the disclosed systems modify parameters of the diffusion neural network.
-
-
-
-
-
-
-
-
-
Search Results
54
records
(took 0.022 seconds)
