-
31.发明申请公开(公告)号：US20180315165A1
公开(公告)日：2018-11-01
申请号：US15821095
申请日：2017-11-22
Applicant: BOE Technology Group Co., Ltd.
Inventor： Pablo Navarrete Michelini , Hanwen Liu , Xiaoyu Li
Abstract: The disclosure discloses an apparatus for upscaling an image, a method for training the same, and a method for upscaling an image, where a convolutional neutral network circuit obtains feature images of the image, a multiplexer upscales the image by integrating every n*n feature images of an input signal into a feature image with a resolution which is n times the resolution of a feature image of the image, where n is an integer greater than 1.
-
32.发明授权公开(公告)号：US12223690B2
公开(公告)日：2025-02-11
申请号：US17773123
申请日：2021-03-18
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Wenhao Zhang , Hanwen Liu , Jingtao Xu
IPC: G06V10/762 , G06V10/74 , G06V10/776 , G06V10/98 , G06V40/16
Abstract: Disclosed are face clustering method and apparatus, image classification storage method, computer-readable storage medium and electronic device. The face clustering method includes: clustering to-be-clustered images, including: acquiring similarity threshold corresponding to quantity level of current image categories in image category library, at least two quantity levels corresponding to different similarity thresholds; judging, according to current similarity threshold and similarity between each to-be-clustered face image and at least one image category in image category library, whether there is image of same category as to-be-clustered face image in image category library; determining, when there is image of same category as to-be-clustered face image, category label of the to-be-clustered face image according to category label of image of same category as to-be-clustered face image; and assigning, when there is no image of same category as to-be-clustered face image, category label to the to-be-clustered face image according to first preset rule.
-
公开(公告)号：US11800053B2
公开(公告)日：2023-10-24
申请号：US17278403
申请日：2020-05-29
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Yunhua Lu , Ran Duan , Guannan Chen , Lijie Zhang , Hanwen Liu
CPC classification number: H04N7/0137 , G06T3/40 , G06T7/246 , G06T7/269 , G06T7/50 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084 , G06T2207/20221
Abstract: The present disclosure relates to the field of information display, and specifically to a method, device, computer readable storage medium, and electronic device for video frame interpolation. The method comprises: obtaining, based on two input frames, two initial optical flow maps corresponding to the two input frames; optimizing the initial optical flow maps to obtain target optical flow maps; obtaining an interpolation frame kernel, two depth maps and two context feature maps based on the two input frames; obtaining an output frame using a frame synthesis method based on the target optical flow maps, the depth maps, the context feature maps, and the interpolation frame kernel.
-
公开(公告)号：US11689693B2
公开(公告)日：2023-06-27
申请号：US17265568
申请日：2020-04-30
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Yunhua Lu , Guannan Chen , Ran Duan , Lijie Zhang , Hanwen Liu
CPC classification number: H04N7/0135 , G06N20/00 , H04N7/0145
Abstract: A video frame interpolation method and device, and a computer-readable storage medium are described. The method includes: inputting at least two image frames into a video frame interpolation model to obtain at least one frame-interpolation image frame, training the initial model using a first loss to obtain a reference model, copying the reference model to obtain three reference models with shared parameters, selecting different target sample images according to a preset rules to train the first/second reference model to obtain a first/second frame-interpolation result; selecting third target sample images from the first/second frame-interpolation result to train the third reference model to obtain the frame-interpolation result, obtaining a total loss of the first training model based on the frame-interpolation result and the sample images, adjusting parameters of the first training model based on the total loss, and using a parameter model via a predetermined number of iterations as the video frame interpolation model.
-
公开(公告)号：US11537849B2
公开(公告)日：2022-12-27
申请号：US16626302
申请日：2019-07-22
Applicant: BOE Technology Group Co., Ltd.
Inventor： Dan Zhu , Lijie Zhang , Pablo Navarre Michelini , Hanwen Liu
Abstract: A computer-implemented method of training a convolutional neural network configured to morph content features of an input image with style features of a style image is provided. The computer-implemented method includes selecting a training style image; extracting style features of the training style image; selecting a training content image; extracting content features of the training content image; processing the training content image through the convolutional neural network to generate a training output image including the content features of the training content image morphed with the style features of the training style image; extracting content features and style features of the training output image; computing a total loss; and tuning the convolutional neural network based on the total loss including a content loss, a style loss, and a regularization loss.
-
Patent Agency Ranking
公开(公告)号：US11361222B2
公开(公告)日：2022-06-14
申请号：US16614547
申请日：2019-06-20
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Pablo Navarrete Michelini , Dan Zhu , Hanwen Liu
IPC: G06N3/00 , G06N3/08 , G06F17/16 , G06N3/04 , G06T3/40 , G06K9/62 , G06T5/00 , G06T5/50 , G06V10/75
Abstract: A cascaded system for classifying an image includes a first cascade layer including a first analysis module coupled to a first input terminal, and a first pooling module coupled to the first analysis module; a second cascade layer including a second analysis module coupled to a second input terminal, and a second pooling module coupled to the first pooling module and the second analysis module; a synthesis layer coupled to the second pooling module, and an activation layer coupled to the synthesis layer.
-
公开(公告)号：US11348005B2
公开(公告)日：2022-05-31
申请号：US16614558
申请日：2019-06-20
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Pablo Navarrete Michelini , Dan Zhu , Hanwen Liu
Abstract: The present disclosure provides a method of training a generative adversarial network. The method includes iteratively enhancing a first noise input in a generative network to generate a first output image; iteratively enhancing a second noise input in the generative network to generate a second output image; transmitting the first output image and a second reference image to a discriminative network, the second reference image corresponding to the first reference image and having a higher resolution than the first reference image; obtaining a first score from the discriminative network based on the second reference image, and a second score from the discriminative network based on the first output image; calculating a loss function of the generative network based on the first score and the second score; and adjusting at least one parameter of the generative network to lower the loss function of the generative network.
-
公开(公告)号：US11328184B2
公开(公告)日：2022-05-10
申请号：US16487885
申请日：2018-10-31
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Pablo Navarrete Michelini , Hanwen Liu
Abstract: Disclosed are an image classification and conversion method, apparatus, image processor and training method thereof, and medium. The image classification method includes receiving a first input image and a second input image; performing image encoding on the first input image by utilizing n stages of encoding units connected in cascades to produce a first output image, wherein n is an integer greater than 1, and wherein as for 1≤i
-
公开(公告)号：US11281938B2
公开(公告)日：2022-03-22
申请号：US16329893
申请日：2018-08-20
Applicant: BOE TECHNOLOGY GROUP CO., LTD
Inventor： Hanwen Liu , Pablo Navarrete Michelini
Abstract: An image processing method includes: obtaining an input image; and performing image conversion processing on the input image by using a generative neural network, to output a converted output image, wherein the generative neural network includes a plurality of processing levels, wherein an output result of an i-th processing level is inputted to an (i+1)-th processing level and a j-th processing level, the j-th processing level further receives an output result of a (j−1)-th processing level, the output result of the (j−1)-th processing level and the output result of the i-th processing level have the same size, wherein i is less than j−1, i and j are positive integers.
-
公开(公告)号：US11189013B2
公开(公告)日：2021-11-30
申请号：US16465294
申请日：2018-12-17
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor： Pablo Navarrete Michelini , Dan Zhu , Hanwen Liu
Abstract: The present disclosure relates to an image processing method. The image processing method may include upscaling a feature image of an input image by an upscaling convolutional network to obtain a upscaled feature image; downscaling the upscaled feature image by a downscaling convolutional network to obtain a downscaled feature image; determining a residual image between the downscaled feature image and the feature image of the input image; upscaling the residual image between the downscaled feature image and the feature image of the input image to obtain an upscaled residual image; correcting the upscaled feature image using the upscaled residual image to obtain a corrected upscaled feature image; and generating a first super-resolution image based on the input image using the corrected upscaled feature image.
-
-
-
-
-
-
-
-
-
Search Results
65
records
(took 0.025 seconds)
