-
公开(公告)号:US20240338796A1
公开(公告)日:2024-10-10
申请号:US18681951
申请日:2023-02-17
Applicant: BOE Technology Group Co., Ltd.
Inventor: Dan Zhu , Mengdi Sun
CPC classification number: G06T5/50 , G06T3/40 , G06T5/92 , G06T7/337 , G06T2207/10144 , G06T2207/20208 , G06T2207/20221
Abstract: A method for reconstructing an HDR image includes: acquiring a plurality of original images with same photographing scene and different exposure degrees; screening out a reference image from the plurality of original images, performing feature alignment processing on remaining original images according to the reference image, and obtaining displacement images of the remaining original images; determining an enhanced image according to the reference image and the displacement images of the remaining original images, wherein the enhanced image is obtained by performing image enhancement processing on a fused image after a down-sampling operation, and the fused image is obtained by performing feature fusion on the reference image and the displacement images of the remaining original images; and reconstructing the HDR images corresponding to the plurality of original images according to the enhanced images.
-
公开(公告)号:US12212882B2
公开(公告)日:2025-01-28
申请号:US18022236
申请日:2022-02-25
Applicant: BOE Technology Group Co., Ltd.
Inventor: Mengdi Sun
Abstract: A video frame interpolation processing method and apparatus thereof, and a non-transitory readable storage medium are disclosed. The method includes: acquiring a target video; acquiring a first frame number set, based on the target video; acquiring at least one speech fragment of a target audio; acquiring a second frame number set, based on the at least one speech fragment of the target audio and the target video; performing frame interpolation on the target video, based on the first frame number set and the second frame number set. The method can avoid the deformation problem caused by picture switch in frame interpolation processing.
-
公开(公告)号:US12190487B2
公开(公告)日:2025-01-07
申请号:US17635263
申请日:2021-04-30
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor: Guannan Chen , Mengdi Sun , Yan Gao , Lijie Zhang
Abstract: An image processing method, an apparatus, an electronic device and a non-transient computer-readable storage medium. The image processing method includes: acquiring an original image; performing a fuzzy processing to the original image to obtain a fuzzy image; performing a high-dynamic-range image to the original image by using a first network model obtained by pre-training, to obtain a first characteristic matrix, wherein the first network model includes a dense residual module and a gate-control-channel conversion module; obtaining an auxiliary characteristic matrix of the original image according to the fuzzy image, wherein the auxiliary characteristic matrix includes detail information of the original image and/or low-frequency information of the original image; obtaining a target image according to the first characteristic matrix and the auxiliary characteristic matrix.
-
公开(公告)号:US12125174B2
公开(公告)日:2024-10-22
申请号:US17626162
申请日:2020-12-24
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor: Guannan Chen , Ran Duan , Mengdi Sun , Lijie Zhang
CPC classification number: G06T5/70 , G06T3/4046 , G06T5/20 , G06T5/50 , G06V10/7715 , G06V40/166 , G06V40/168 , G06T2207/20028 , G06T2207/20081 , G06T2207/20084 , G06T2207/20221
Abstract: An image processing method and device, and a computer-readable storage medium are disclosed. The method includes: performing a channel expansion process on the input image to obtain a first intermediate image; performing a channel decomposition process for multiple times based on the first intermediate image, wherein each time of channel decomposition process includes: decomposing an image to be processed into a first decomposition image and a second decomposition image; concatenating first decomposition images generated in each time of channel decomposition process and second decomposition image generated in the last time of channel decomposition process to obtain a concatenated image; performing a post-processing process on the concatenated image to obtain a second intermediate image; and fusing the second intermediate image with the input image to obtain the first output image.
-
5.
公开(公告)号:US20240275909A1
公开(公告)日:2024-08-15
申请号:US18022236
申请日:2022-02-25
Applicant: BOE Technology Group Co., Ltd.
Inventor: Mengdi Sun
CPC classification number: H04N5/268 , H04N5/278 , H04N7/0135
Abstract: A video frame interpolation processing method and apparatus thereof, and a non-transitory readable storage medium. The method includes: (S101) acquiring a target video; (S102) acquiring a first frame number set, based on the target video; (S103) acquiring at least one speech fragment of a target audio; (S104) acquiring a second frame number set, based on the at least one speech fragment of the target audio and the target video; (S105) performing frame interpolation on the target video, based on the first frame number set and the second frame number set. The target video includes a plurality of video frames, each of the plurality of video frames has a corresponding frame number, and frame numbers of the plurality of video frames increase progressively in time order. The first frame number set includes at least one first frame number, and each of the at least one first frame number corresponds to a video frame with picture switch. The target audio corresponds to the target video in time domain. The second frame number set includes at least one second frame number, and each of the at least one second frame number corresponds to a video frame with subtitle switch, so as to avoid the deformation problem caused by picture switch in frame interpolation processing.
-
公开(公告)号:US20230342892A1
公开(公告)日:2023-10-26
申请号:US17635263
申请日:2021-04-30
Applicant: BOE TECHNOLOGY GROUP CO., LTD.
Inventor: Guannan Chen , Mengdi Sun , Yan Gao , Lijie Zhang
CPC classification number: G06T5/007 , G06T5/20 , G06V10/761 , G06T2207/20081 , G06T2207/20208
Abstract: An image processing method, an apparatus, an electronic device and a non-transient computer-readable storage medium. The image processing method includes: (S11) acquiring an original image; (S12) performing a fuzzy processing to the original image to obtain a fuzzy image; (S13) performing a high-dynamic-range image to the original image by using a first network model obtained by pre-training, to obtain a first characteristic matrix, wherein the first network model includes a dense residual module and a gate-control-channel conversion module; (S14) obtaining an auxiliary characteristic matrix of the original image according to the fuzzy image, wherein the auxiliary characteristic matrix includes detail information of the original image and/or low-frequency information of the original image; (S15) obtaining a target image according to the first characteristic matrix and the auxiliary characteristic matrix.
-
-
-
-
-