-
公开(公告)号:US20220366841A1
公开(公告)日:2022-11-17
申请号:US17417153
申请日:2020-11-09
发明人: Wenbin CHEN , Rongjian YAN , Guangjun SONG , Zhaowei YU , Yamin YANG , Wenqiang ZHANG
IPC分类号: G09G3/3208 , G09G5/10
摘要: A driving method includes, at a first display brightness value, inputting a pulse-width modulation signal with a duty ratio of X, and controlling a light-emitting driving current of a sub-pixel unit to be M, wherein X and M are obtained according to a first modulation rule; and at a second display brightness value, inputting the pulse-width modulation signal with a duty ratio of Y1, and controlling the light-emitting driving current of the sub-pixel unit to be N1, wherein the first display brightness value is greater than the second one, wherein, when the duty ratio and the light-emitting driving current corresponding to the second display brightness value are obtained according to the first modulation rule, the duty ratio corresponding to the second display brightness value is Y2, the light-emitting driving current corresponding to the second display brightness value is N2, Y1 is smaller than Y2, and N1 is greater than N2.
-
公开(公告)号:US20220100304A1
公开(公告)日:2022-03-31
申请号:US17486827
申请日:2021-09-27
发明人: Zhaowei YU , Qinhe WEI , Rongjian YAN , Wenbin CHEN
摘要: A display substrate is provided. The display substrate includes: a base substrate; a pixel defining layer disposed on the base substrate, wherein the pixel defining layer defines a plurality of sub-pixel areas and has a groove therein; and a touch structure disposed in the groove, wherein the touch structure is configured to provide a touch function.
-
公开(公告)号:US20240231529A1
公开(公告)日:2024-07-11
申请号:US18617645
申请日:2024-03-26
发明人: Zhaowei YU , Qinhe WEI , Rongjian YAN , Wenbin CHEN
IPC分类号: G06F3/041 , H10K50/84 , H10K59/122 , H10K59/124 , H10K59/40 , H10K71/00 , H10K77/10
CPC分类号: G06F3/0412 , H10K50/84 , H10K59/122 , H10K59/124 , H10K59/40 , H10K71/00 , H10K77/111
摘要: A display substrate is provided. The display substrate includes: a base substrate; a pixel defining layer disposed on the base substrate, wherein the pixel defining layer comprises a plurality of barriers and defines a plurality of sub-pixel areas, some or all of the barriers have grooves therein; and a touch structure disposed in the groove, wherein the touch structure is configured to provide a touch function.
-
公开(公告)号:US20220375405A1
公开(公告)日:2022-11-24
申请号:US17767061
申请日:2021-06-10
发明人: Wenqiang ZHANG , Rongjian YAN , Wenbin CHEN
IPC分类号: G09G3/3233 , G09G3/20 , G09G3/3291
摘要: A driving method of a display panel includes: determining a brightness band of the display panel, wherein brightness bands include a first brightness band to an Nth brightness band, maximum grayscale brightness of the first brightness band to the Nth brightness band decreases sequentially, and each brightness band includes three Gamma correction curves respectively corresponding to a first light emitting unit, a second light emitting unit, and a third light emitting unit each of an (N−M)th brightness band to the Nth brightness band also corresponds to at least one duty ratio; determining an input data voltage corresponding to at least one light emitting unit based on a Gamma correction curve that corresponds to the determined brightness band and an image to be displayed; and driving the display panel to display the image based on the determined input data voltage, or the determined input data voltage and the duty ratio.
-
公开(公告)号:US20240233074A9
公开(公告)日:2024-07-11
申请号:US18396866
申请日:2023-12-27
发明人: Pablo NAVARRETE MICHELINI , Wenbin CHEN , Hanwen LIU , Dan ZHU
IPC分类号: G06T3/4046 , G06N3/08 , G06T3/4053 , G06T5/50
CPC分类号: G06T3/4046 , G06N3/08 , G06T3/4053 , G06T5/50
摘要: An image processing method, an image processing device, a training method of a neural network, an image processing method based on a combined neural network model, a constructing method of a combined neural network model, a neural network processor, and a storage medium are provided. The image processing method includes: obtaining, based on an input image, initial feature images of N stages with resolutions from high to low, N is a positive integer and N>2; performing, based on initial feature images of second to N-th stages, cyclic scaling processing on an initial feature image of a first stage, to obtain an intermediate feature image; and performing merging processing on the intermediate feature image to obtain an output image. The cyclic scaling processing includes hierarchically-nested scaling processing of N−1 stages, and scaling processing of each stage includes down-sampling processing, concatenating processing, up-sampling processing, and residual link addition processing.
-
公开(公告)号:US20240135490A1
公开(公告)日:2024-04-25
申请号:US18396866
申请日:2023-12-27
发明人: Pablo NAVARRETE MICHELINI , Wenbin CHEN , Hanwen LIU , Dan ZHU
IPC分类号: G06T3/4046 , G06N3/08 , G06T3/4053 , G06T5/50
CPC分类号: G06T3/4046 , G06N3/08 , G06T3/4053 , G06T5/50
摘要: An image processing method, an image processing device, a training method of a neural network, an image processing method based on a combined neural network model, a constructing method of a combined neural network model, a neural network processor, and a storage medium are provided. The image processing method includes: obtaining, based on an input image, initial feature images of N stages with resolutions from high to low, N is a positive integer and N>2; performing, based on initial feature images of second to N-th stages, cyclic scaling processing on an initial feature image of a first stage, to obtain an intermediate feature image; and performing merging processing on the intermediate feature image to obtain an output image. The cyclic scaling processing includes hierarchically-nested scaling processing of N−1 stages, and scaling processing of each stage includes down-sampling processing, concatenating processing, up-sampling processing, and residual link addition processing.
-
公开(公告)号:US20220084166A1
公开(公告)日:2022-03-17
申请号:US17419350
申请日:2020-10-13
发明人: Pablo NAVARRETE MICHELINI , Wenbin CHEN , Hanwen LIU , Dan ZHU
摘要: An image processing method, an image processing device, a training method of a neural network, an image processing method based on a combined neural network model, a constructing method of a combined neural network model, a neural network processor, and a storage medium are provided. The image processing method includes: obtaining, based on an input image, initial feature images of N stages with resolutions from high to low, where N is a positive integer and N>2, performing, based on initial feature images of second to N-th stages, cyclic scaling processing on an initial feature image of a first stage, to obtain an intermediate feature image; and preforming merging processing on the intermediate feature image to obtain an output image. The cyclic scaling processing includes hierarchically-nested scaling processing of N−1 stages, and scaling processing of each stage includes down-sampling processing, concatenating processing, up-sampling processing, and residual link addition processing.
-
公开(公告)号:US20220100576A1
公开(公告)日:2022-03-31
申请号:US17407145
申请日:2021-08-19
发明人: Wenbin CHEN , Yan GAO , Guannan CHEN
IPC分类号: G06F9/50 , H04N19/124 , H04N19/176 , G06F9/48
摘要: A video processing method and device, electronic equipment and a storage medium, which are applied to the technical field of computers. The method comprises: acquiring video data to be processed; generating video enhancement tasks corresponding to each video frame in the video data to be processed, the video enhancement task comprising a plurality of video enhancement subtasks; and simultaneously executing at least two different video enhancement subtasks of the plurality of video frames in a multi-thread concurrent manner, a single thread correspondingly executing one video enhancement subtask.
-
-
-
-
-
-
-