-
公开(公告)号：US20230129341A1
公开(公告)日：2023-04-27
申请号：US17584233
申请日：2022-01-25
Applicant: Adobe Inc.
Inventor： Betty Leong , Hyunghwan Byun , Alan L Erickson , Chih-Yao Hsieh , Sarah Kong , Seyed Morteza Safdarnejad , Salil Tambe , Yilin Wang , Zijun Wei , Zhengyun Zhang
IPC: G06T7/10 , G06F3/04842 , G06T3/40
Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate preliminary object masks for objects in an image, surface the preliminary object masks as object mask previews, and on-demand converts preliminary object masks into refined object masks. Indeed, in one or more implementations, an object mask preview and on-demand generation system automatically detects objects in an image. For the detected objects, the object mask preview and on-demand generation system generates preliminary object masks for the detected objects of a first lower resolution. The object mask preview and on-demand generation system surfaces a given preliminary object mask in response to detecting a first input. The object mask preview and on-demand generation system also generates a refined object mask of a second higher resolution in response to detecting a second input.
-
公开(公告)号：US11544831B2
公开(公告)日：2023-01-03
申请号：US16984992
申请日：2020-08-04
Applicant: Adobe Inc.
Inventor： Yilin Wang , Zhe Lin , Zhaowen Wang , Xin Lu , Xiaohui Shen , Chih-Yao Hsieh
Abstract: The present disclosure relates to training and utilizing an image exposure transformation network to generate a long-exposure image from a single short-exposure image (e.g., still image). In various embodiments, the image exposure transformation network is trained using adversarial learning, long-exposure ground truth images, and a multi-term loss function. In some embodiments, the image exposure transformation network includes an optical flow prediction network and/or an appearance guided attention network. Trained embodiments of the image exposure transformation network generate realistic long-exposure images from single short-exposure images without additional information.
-
公开(公告)号：US20220292654A1
公开(公告)日：2022-09-15
申请号：US17200338
申请日：2021-03-12
Applicant: Adobe Inc.
Inventor： He Zhang , Yifan Jiang , Yilin Wang , Jianming Zhang , Kalyan Sunkavalli , Sarah Kong , Su Chen , Sohrab Amirghodsi , Zhe Lin
Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately, efficiently, and flexibly generating harmonized digital images utilizing a self-supervised image harmonization neural network. In particular, the disclosed systems can implement, and learn parameters for, a self-supervised image harmonization neural network to extract content from one digital image (disentangled from its appearance) and appearance from another from another digital image (disentangled from its content). For example, the disclosed systems can utilize a dual data augmentation method to generate diverse triplets for parameter learning (including input digital images, reference digital images, and pseudo ground truth digital images), via cropping a digital image with perturbations using three-dimensional color lookup tables (“LUTs”). Additionally, the disclosed systems can utilize the self-supervised image harmonization neural network to generate harmonized digital images that depict content from one digital image having the appearance of another digital image.
-
公开(公告)号：US20220284321A1
公开(公告)日：2022-09-08
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.
-
公开(公告)号：US20210264278A1
公开(公告)日：2021-08-26
申请号：US16799191
申请日：2020-02-24
Applicant: Adobe Inc.
Inventor： Shikun Liu , Zhe Lin , Yilin Wang , Jianming Zhang , Federico Perazzi
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.
-
Patent Agency Ranking
公开(公告)号：US10783622B2
公开(公告)日：2020-09-22
申请号：US15962735
申请日：2018-04-25
Applicant: Adobe Inc.
Inventor： Yilin Wang , Zhe Lin , Zhaowen Wang , Xin Lu , Xiaohui Shen , Chih-Yao Hsieh
Abstract: The present disclosure relates to training and utilizing an image exposure transformation network to generate a long-exposure image from a single short-exposure image (e.g., still image). In various embodiments, the image exposure transformation network is trained using adversarial learning, long-exposure ground truth images, and a multi-term loss function. In some embodiments, the image exposure transformation network includes an optical flow prediction network and/or an appearance guided attention network. Trained embodiments of the image exposure transformation network generate realistic long-exposure images from single short-exposure images without additional information.
-
17.发明授权公开(公告)号：US12299844B2
公开(公告)日：2025-05-13
申请号：US18440248
申请日：2024-02-13
Applicant: Adobe Inc.
Inventor： He Zhang , Yifan Jiang , Yilin Wang , Jianming Zhang , Kalyan Sunkavalli , Sarah Kong , Su Chen , Sohrab Amirghodsi , Zhe Lin
Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately, efficiently, and flexibly generating harmonized digital images utilizing a self-supervised image harmonization neural network. In particular, the disclosed systems can implement, and learn parameters for, a self-supervised image harmonization neural network to extract content from one digital image (disentangled from its appearance) and appearance from another from another digital image (disentangled from its content). For example, the disclosed systems can utilize a dual data augmentation method to generate diverse triplets for parameter learning (including input digital images, reference digital images, and pseudo ground truth digital images), via cropping a digital image with perturbations using three-dimensional color lookup tables (“LUTs”). Additionally, the disclosed systems can utilize the self-supervised image harmonization neural network to generate harmonized digital images that depict content from one digital image having the appearance of another digital image.
-
公开(公告)号：US12148074B2
公开(公告)日：2024-11-19
申请号：US17503671
申请日：2021-10-18
Applicant: Adobe Inc.
Inventor： He Zhang , Jeya Maria Jose Valanarasu , Jianming Zhang , Jose Ignacio Echevarria Vallespi , Kalyan Sunkavalli , Yilin Wang , Yinglan Ma , Zhe Lin , Zijun Wei
IPC: G06T11/60 , G06F3/04842 , G06F3/04845 , G06N3/08 , G06V10/40 , G06V10/75
Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating harmonized digital images utilizing an object-to-object harmonization neural network. For example, the disclosed systems implement, and learn parameters for, an object-to-object harmonization neural network to combine a style code from a reference object with features extracted from a target object. Indeed, the disclosed systems extract a style code from a reference object utilizing a style encoder neural network. In addition, the disclosed systems generate a harmonized target object by applying the style code of the reference object to a target object utilizing an object-to-object harmonization neural network.
-
公开(公告)号：US20240169541A1
公开(公告)日：2024-05-23
申请号：US18056987
申请日：2022-11-18
Applicant: ADOBE INC.
Inventor： Jianming Zhang , Qing Liu , Yilin Wang , Zhe Lin , Bowen Zhang
IPC: G06T7/10
CPC classification number: G06T7/10 , G06T2207/20081
Abstract: Systems and methods for instance segmentation are described. Embodiments include identifying an input image comprising an object that includes a visible region and an occluded region that is concealed in the input image. A mask network generates an instance mask for the input image that indicates the visible region of the object. A diffusion model then generates a segmentation mask for the input image based on the instance mask. The segmentation mask indicates a completed region of the object that includes the visible region and the occluded region.
-
公开(公告)号：US20230132180A1
公开(公告)日：2023-04-27
申请号：US17585140
申请日：2022-01-26
Applicant: Adobe Inc.
Inventor： Chih-Yao Hsieh , Yilin Wang
Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that upsample and refine segmentation masks. Indeed, in one or more implementations, a segmentation mask refinement and upsampling system upsamples a preliminary segmentation mask utilizing a patch-based refinement process to generate a patch-based refined segmentation mask. The segmentation mask refinement and upsampling system then fuses the patch-based refined segmentation mask with an upsampled version of the preliminary segmentation mask. By fusing the patch-based refined segmentation mask with the upsampled preliminary segmentation mask, the segmentation mask refinement and upsampling system maintains a global perspective and helps avoid artifacts due to the local patch-based refinement process.
-
-
-
-
-
-
-
-
-
Search Results
46
records
(took 0.034 seconds)
