-
公开(公告)号：US20190287283A1
公开(公告)日：2019-09-19
申请号：US15921998
申请日：2018-03-15
Applicant: Adobe Inc.
Inventor： Zhe Lin , Xin Lu , Xiaohui Shen , Jimei Yang , Jiahui Yu
Abstract: Certain embodiments involve using an image completion neural network to perform user-guided image completion. For example, an image editing application accesses an input image having a completion region to be replaced with new image content. The image editing application also receives a guidance input that is applied to a portion of a completion region. The image editing application provides the input image and the guidance input to an image completion neural network that is trained to perform image-completion operations using guidance input. The image editing application produces a modified image by replacing the completion region of the input image with the new image content generated with the image completion network. The image editing application outputs the modified image having the new image content.
-
公开(公告)号：US10387776B2
公开(公告)日：2019-08-20
申请号：US15456348
申请日：2017-03-10
Applicant: ADOBE INC.
Inventor： Zhe Lin , Yufei Wang , Scott Cohen , Xiaohui Shen
Abstract: Provided are systems and techniques that provide an output phrase describing an image. An example method includes creating, with a convolutional neural network, feature maps describing image features in locations in the image. The method also includes providing a skeletal phrase for the image by processing the feature maps with a first long short-term memory (LSTM) neural network trained based on a first set of ground truth phrases which exclude attribute words. Then, attribute words are provided by processing the skeletal phrase and the feature maps with a second LSTM neural network trained based on a second set of ground truth phrases including words for attributes. Then, the method combines the skeletal phrase and the attribute words to form the output phrase.
-
公开(公告)号：US20250069203A1
公开(公告)日：2025-02-27
申请号：US18454850
申请日：2023-08-24
Applicant: ADOBE INC.
Inventor： Yuqian Zhou , Krishna Kumar Singh , Benjamin Delarre , Zhe Lin , Jingwan Lu , Taesung Park , Sohrab Amirghodsi , Elya Shechtman
Abstract: A method, non-transitory computer readable medium, apparatus, and system for image generation are described. An embodiment of the present disclosure includes obtaining an input image, an inpainting mask, and a plurality of content preservation values corresponding to different regions of the inpainting mask, and identifying a plurality of mask bands of the inpainting mask based on the plurality of content preservation values. An image generation model generates an output image based on the input image and the inpainting mask. The output image is generated in a plurality of phases. Each of the plurality of phases uses a corresponding mask band of the plurality of mask bands as an input.
-
公开(公告)号：US12223661B2
公开(公告)日：2025-02-11
申请号：US17735728
申请日：2022-05-03
Applicant: ADOBE INC.
Inventor： Lu Zhang , Jianming Zhang , Zhe Lin , Radomir Mech
Abstract: Systems and methods provide editing operations in a smart editing system that may generate a focal point within a mask of an object for each frame of a video segment and perform editing effects on the frames of the video segment to quickly provide users with natural video editing effects. An eye-gaze network may produce a hotspot map of predicted focal points in a video frame. These predicted focal points may then be used by a gaze-to-mask network to determine objects in the image and generate an object mask for each of the detected objects. This process may then be repeated to effectively track the trajectory of objects and object focal points in videos. Based on the determined trajectory of an object in a video clip and editing parameters, the editing engine may produce editing effects relative to an object for the video clip.
-
公开(公告)号：US12223439B2
公开(公告)日：2025-02-11
申请号：US17190668
申请日：2021-03-03
Applicant: ADOBE INC.
Inventor： Xin Yuan , Zhe Lin , Jason Wen Yong Kuen , Jianming Zhang , Yilin Wang , Ajinkya Kale , Baldo Faieta
Abstract: Systems and methods for multi-modal representation learning are described. One or more embodiments provide a visual representation learning system trained using machine learning techniques. For example, some embodiments of the visual representation learning system are trained using cross-modal training tasks including a combination of intra-modal and inter-modal similarity preservation objectives. In some examples, the training tasks are based on contrastive learning techniques.
-
Patent Agency Ranking
公开(公告)号：US12204610B2
公开(公告)日：2025-01-21
申请号：US17650967
申请日：2022-02-14
Applicant: Adobe Inc.
Inventor： Zhe Lin , Haitian Zheng , Jingwan Lu , Scott Cohen , Jianming Zhang , Ning Xu , Elya Shechtman , Connelly Barnes , Sohrab Amirghodsi
IPC: G06K9/00 , G06F18/214 , G06N3/08 , G06T5/77 , G06T7/11
Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for training a generative inpainting neural network to accurately generate inpainted digital images via object-aware training and/or masked regularization. For example, the disclosed systems utilize an object-aware training technique to learn parameters for a generative inpainting neural network based on masking individual object instances depicted within sample digital images of a training dataset. In some embodiments, the disclosed systems also (or alternatively) utilize a masked regularization technique as part of training to prevent overfitting by penalizing a discriminator neural network utilizing a regularization term that is based on an object mask. In certain cases, the disclosed systems further generate an inpainted digital image utilizing a trained generative inpainting model with parameters learned via the object-aware training and/or the masked regularization.
-
公开(公告)号：US20240428384A1
公开(公告)日：2024-12-26
申请号：US18212992
申请日：2023-06-22
Applicant: Adobe Inc.
Inventor： Yuqian Zhou , Zhe Lin , Xiaoyang Liu , Sohrab Amirghodsi , Qing Liu , Lingzhi Zhang , Elya Schechtman , Connelly Stuart Barnes
Abstract: Inpainting dispatch techniques for digital images are described. In one or more examples, an inpainting system includes a plurality of inpainting modules. The inpainting modules are configured to employ a variety of different techniques, respectively, as part of performing an inpainting operation. An inpainting dispatch module is also included as part of the inpainting system that is configured to select which of the plurality of inpainting modules are to be used to perform an inpainting operation for one or more regions in a digital image, automatically and without user intervention.
-
公开(公告)号：US20240404013A1
公开(公告)日：2024-12-05
申请号：US18515378
申请日：2023-11-21
Applicant: ADOBE INC.
Inventor： Yuqian Zhou , Krishna Kumar Singh , Zhe Lin , Qing Liu , Zhifei Zhang , Sohrab Amirghodsi , Elya Shechtman , Jingwan Lu
Abstract: Embodiments include systems and methods for generative image filling based on text and a reference image. In one aspect, the system obtains an input image, a reference image, and a text prompt. Then, the system encodes the reference image to obtain an image embedding and encodes the text prompt to obtain a text embedding. Subsequently, a composite image is generated based on the input image, the image embedding, and the text embedding.
-
公开(公告)号：US12141952B2
公开(公告)日：2024-11-12
申请号：US17957639
申请日：2022-09-30
Applicant: Adobe Inc.
Inventor： Akhilesh Kumar , Zhe Lin , William Lawrence Marino
Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for detecting and classifying an exposure defect in an image using neural networks trained via a limited amount of labeled training images. An image may be applied to a first neural network to determine whether the images includes an exposure defect. Detected defective image may be applied to a second neural network to determine an exposure defect classification for the image. The exposure defect classification can includes severe underexposure, medium underexposure, mild underexposure, mild overexposure, medium overexposure, severe overexposure, and/or the like. The image may be presented to a user along with the exposure defect classification.
-
公开(公告)号：US20240362757A1
公开(公告)日：2024-10-31
申请号：US18307546
申请日：2023-04-26
Applicant: Adobe Inc.
Inventor： Sohrab Amirghodsi , Lingzhi Zhang , Connelly Barnes , Elya Shechtman , Yuqian Zhou , Zhe Lin
CPC classification number: G06T5/77 , G06T5/30 , G06T5/50 , G06T7/11 , G06T2207/20076 , G06T2207/20081 , G06T2207/20084
Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for inpainting digital images utilizing mask-robust machine-learning models. In particular, in one or more embodiments, the disclosed systems obtain an initial mask for an object depicted in a digital image. Additionally, in some embodiments, the disclosed systems generate, utilizing a mask-robust inpainting machine-learning model, an inpainted image from the digital image and the initial mask. Moreover, in some implementations, the disclosed systems generate a relaxed mask that expands the initial mask. Furthermore, in some embodiments, the disclosed systems generate a modified image by compositing the inpainted image and the digital image utilizing the relaxed mask.
-
-
-
-
-
-
-
-
-
Search Results
388
records
(took 0.12 seconds)
