-
公开(公告)号：US10672164B2
公开(公告)日：2020-06-02
申请号：US15785386
申请日：2017-10-16
Applicant: Adobe Inc.
Inventor： Zhe Lin , Xin Lu , Xiaohui Shen , Jimei Yang , Jiahui Yu
Abstract: Predicting patch displacement maps using a neural network is described. Initially, a digital image on which an image editing operation is to be performed is provided as input to a patch matcher having an offset prediction neural network. From this image and based on the image editing operation for which this network is trained, the offset prediction neural network generates an offset prediction formed as a displacement map, which has offset vectors that represent a displacement of pixels of the digital image to different locations for performing the image editing operation. Pixel values of the digital image are copied to the image pixels affected by the operation by: determining the vectors pixels that correspond to the image pixels affected by the image editing operation and mapping the pixel values of the image pixels represented by the determined offset vectors to the affected pixels. According to this mapping, the pixel values of the affected pixels are set, effective to perform the image editing operation.
-
公开(公告)号：US10482639B2
公开(公告)日：2019-11-19
申请号：US15438147
申请日：2017-02-21
Applicant: Adobe Inc.
Inventor： Yijun Li , Chen Fang , Jimei Yang , Zhaowen Wang , Xin Lu
Abstract: In some embodiments, techniques for synthesizing an image style based on a plurality of neural networks are described. A computer system selects a style image based on user input that identifies the style image. The computer system generates an image based on a generator neural network and a loss neural network. The generator neural network outputs the synthesized image based on a noise vector and the style image and is trained based on style features generated from the loss neural network. The loss neural network outputs the style features based on a training image. The training image and the style image have a same resolution. The style features are generated at different resolutions of the training image. The computer system provides the synthesized image to a user device in response to the user input.
-
公开(公告)号：US10445921B1
公开(公告)日：2019-10-15
申请号：US16007898
申请日：2018-06-13
Applicant: Adobe Inc.
Inventor： Yijun Li , Chen Fang , Jimei Yang , Zhaowen Wang , Xin Lu
Abstract: Transferring motion between consecutive frames to a digital image is leveraged in a digital medium environment. A digital image and at least a portion of the digital video are exposed to a motion transfer model. The portion of the digital video includes at least a first digital video frame and a second digital video frame that is consecutive to the first digital video frame. Flow data between the first digital video frame and the second digital image frame is extracted, and the flow data is then processed to generate motion features representing motion between the first digital video frame and the second digital video frame. The digital image is processed to generate image features of the digital image. Motion of the digital video is then transferred to the digital image by combining the motion features with the image features to generate a next digital image frame for the digital image.
-
公开(公告)号：US10410351B2
公开(公告)日：2019-09-10
申请号：US16116609
申请日：2018-08-29
Applicant: Adobe Inc.
Inventor： Zhe Lin , Xin Lu , Xiaohui Shen , Jimei Yang , Chenxi Liu
Abstract: The invention is directed towards segmenting images based on natural language phrases. An image and an n-gram, including a sequence of tokens, are received. An encoding of image features and a sequence of token vectors are generated. A fully convolutional neural network identifies and encodes the image features. A word embedding model generates the token vectors. A recurrent neural network (RNN) iteratively updates a segmentation map based on combinations of the image feature encoding and the token vectors. The segmentation map identifies which pixels are included in an image region referenced by the n-gram. A segmented image is generated based on the segmentation map. The RNN may be a convolutional multimodal RNN. A separate RNN, such as a long short-term memory network, may iteratively update an encoding of semantic features based on the order of tokens. The first RNN may update the segmentation map based on the semantic feature encoding.
-
公开(公告)号：US12154379B2
公开(公告)日：2024-11-26
申请号：US18306439
申请日：2023-04-25
Applicant: Adobe Inc.
Inventor： Jinoh Oh , Xin Lu , Gahye Park , Jen-Chan Jeff Chien , Yumin Jia
Abstract: The present disclosure describes systems, non-transitory computer-readable media, and methods for utilizing a machine learning model trained to determine subtle pose differentiations to analyze a repository of captured digital images of a particular user to automatically capture digital images portraying the user. For example, the disclosed systems can utilize a convolutional neural network to determine a pose/facial expression similarity metric between a sample digital image from a camera viewfinder stream of a client device and one or more previously captured digital images portraying the user. The disclosed systems can determine that the similarity metric satisfies a similarity threshold, and automatically capture a digital image utilizing a camera device of the client device. Thus, the disclosed systems can automatically and efficiently capture digital images, such as selfies, that accurately match previous digital images portraying a variety of unique facial expressions specific to individual users.
-
Patent Agency Ranking
公开(公告)号：US11875260B2
公开(公告)日：2024-01-16
申请号：US15895795
申请日：2018-02-13
Applicant: ADOBE INC.
Abstract: The architectural complexity of a neural network is reduced by selectively pruning channels. A cost metric for a convolution layer is determined. The cost metric indicates a resource cost per channel for the channels of the layer. Training the neural network includes, for channels of the layer, updating a channel-scaling coefficient based on the cost metric. The channel-scaling coefficient linearly scales the output of the channel. A constant channel is identified based on the channel-scaling coefficients. The neural network is updated by pruning the constant channel. Model weights are updated via a stochastic gradient descent of a training loss function evaluated on training data. The channel-scaling coefficients are updated via an iterative-thresholding algorithm that penalizes a batch normalization loss function based on the cost metric for the layer and a norm of the channel-scaling coefficients. When the layer is batch normalized, the channel-scaling coefficients are batch normalization scaling coefficients.
-
公开(公告)号：US20230274400A1
公开(公告)日：2023-08-31
申请号：US18298146
申请日：2023-04-10
Applicant: Adobe Inc.
Inventor： Sheng-Wei Huang , Wentian Zhao , Kun Wan , Zichuan Liu , Xin Lu , Jen-Chan Jeff Chien
IPC: G06T5/00 , G06T7/73 , G06F18/2134 , H04N23/63
CPC classification number: G06T5/005 , G06F18/2134 , G06T7/73 , H04N23/631 , G06T2207/10016 , G06T2207/20081
Abstract: The present disclosure describes systems, non-transitory computer-readable media, and methods for accurately and efficiently removing objects from digital images taken from a camera viewfinder stream. For example, the disclosed systems access digital images from a camera viewfinder stream in connection with an undesired moving object depicted in the digital images. The disclosed systems generate a temporal window of the digital images concatenated with binary masks indicating the undesired moving object in each digital image. The disclosed systems further utilizes a generator as part of a 3D to 2D generative adversarial neural network in connection with the temporal window to generate a target digital image with the region associated with the undesired moving object in-painted. In at least one embodiment, the disclosed systems provide the target digital image to a camera viewfinder display to show a user how a future digital photograph will look without the undesired moving object.
-
公开(公告)号：US11676283B2
公开(公告)日：2023-06-13
申请号：US17660361
申请日：2022-04-22
Applicant: Adobe Inc.
Inventor： Zichuan Liu , Wentian Zhao , Shitong Wang , He Qin , Yumin Jia , Yeojin Kim , Xin Lu , Jen-Chan Chien
IPC: G06T7/11
CPC classification number: G06T7/11 , G06T2207/20084
Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate refined segmentation masks for digital visual media items. For example, in one or more embodiments, the disclosed systems utilize a segmentation refinement neural network to generate an initial segmentation mask for a digital visual media item. The disclosed systems further utilize the segmentation refinement neural network to generate one or more refined segmentation masks based on uncertainly classified pixels identified from the initial segmentation mask. To illustrate, in some implementations, the disclosed systems utilize the segmentation refinement neural network to redetermine whether a set of uncertain pixels corresponds to one or more objects depicted in the digital visual media item based on low-level (e.g., local) feature values extracted from feature maps generated for the digital visual media item.
-
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：US20220164666A1
公开(公告)日：2022-05-26
申请号：US17100651
申请日：2020-11-20
Applicant: Adobe Inc.
Inventor： Zichuan Liu , Kun Wan , Xin Lu
Abstract: A method for performing efficient mixed-precision search for an artificial neural network (ANN) includes training the ANN by sampling selected candidate quantizers of a bank of candidate quantizer and updating network parameters for a next iteration based on outputs of layers of the ANN. The outputs are computed by processing quantized data with operators (e.g., convolution). The quantizers converge to optimal bit-widths that reduce classification losses bounded by complexity constrains.
-
-
-
-
-
-
-
-
-
Search Results
56
records
(took 0.018 seconds)
