公开(公告)号：US20250022096A1

公开(公告)日：2025-01-16

申请号：US18714033

申请日：2022-11-25

Applicant: BEIJING ZITIAO NETWORK TECHNOLOGY CO., LTD.

Inventor： Hang DONG

IPC: G06T3/4053 ,  G06T5/50 ,  G06V10/44

Abstract: Embodiments of the present disclosure relate to a GAN-based super-resolution image processing method and apparatus, a device, and a medium. The method includes: obtaining a first feature of a positive sample image corresponding to an input sample image and a third feature corresponding to a reference sample image; determining a binary cross entropy (BCE) loss function based on the first feature and the third feature, extracting a fourth feature corresponding to the positive sample image, a fifth feature corresponding to a negative sample image, and a sixth feature corresponding to the reference sample image, and determining a second contrastive learning loss function based on the fourth feature, the fifth feature, and the sixth feature; and training parameters of a generative model based on the BCE loss function and the second contrastive learning loss function to obtain a target super-resolution network, so that super-resolution processing is performed on a test image based on the target super-resolution network to obtain a target super-resolution image.

公开(公告)号：US20240273852A1

公开(公告)日：2024-08-15

申请号：US18562821

申请日：2022-05-19

Applicant: BEIJING ZITIAO NETWORK TECHNOLOGY CO., LTD.

Inventor： Hang DONG

IPC: G06V10/24 ,  G06V10/74 ,  G06V10/77 ,  G06V10/82

CPC classification number: G06V10/24 ,  G06V10/761 ,  G06V10/7715 ,  G06V10/82

Abstract: An image alignment method and device, relating to the technical field of image processing. The method comprises: obtaining a target feature comprising feature points corresponding to pixel points in a target image and a reference feature comprising feature points corresponding to pixel points in a reference image; obtaining a similarity feature according to the target feature and the reference feature, the similarity feature comprising the similarity between the feature points in the target feature and a corresponding related feature point; predicting a convolutional layer according to the similarity feature, the target feature, and an offset, and obtaining an offset of the target feature and the reference feature; and aligning the reference feature with the target feature according to the offset and the deformable convolutional layer.

公开(公告)号：US20250078207A1

公开(公告)日：2025-03-06

申请号：US18725733

申请日：2022-12-27

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Hang DONG

IPC: G06T5/50 ,  G06T5/60

Abstract: The embodiments of the present disclosure relate to a video frame repair method, apparatus, device, storage medium, and program product. The method comprises: acquiring a video frame group from a video, wherein the video frame group comprises the target video frame and video frames adjacent to the target video frame; inputting the video frame group into an attention transformation network to obtain a video frame group to be fused, wherein the attention transformation network comprises a set of attention transformation modules that are connected in series, an input of the attention transformation network is an input of a first attention transformation module in the set, and the video frame group comprises a video frame that is output by one or more-attention transformation modules and corresponds to the target video frame; and processing the video frame group to be fused to obtain a repaired target video frame.

公开(公告)号：US20250166139A1

公开(公告)日：2025-05-22

申请号：US18723398

申请日：2022-12-22

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Hang DONG

IPC: G06T5/73 ,  G06T3/40 ,  G06T5/50 ,  G06T5/60

Abstract: A blurry video repair method and apparatus relate to the technical field of image processing. The method comprises: performing feature extraction on a target video frame of a video to be repaired, so as to acquire an intrinsic feature of the target video frame; acquiring a forward hidden variable set of the target video frame according to the intrinsic feature and a first hidden variable set; acquiring a backward hidden variable set of the target video frame according to the intrinsic feature and a second hidden variable set; acquiring an enhanced feature of the target video frame according to the intrinsic feature and the forward hidden variable set and backward hidden variable set of the target video frame; and performing additive fusion on the enhanced feature of the target video frame and the target video frame, so as to acquire a deblurred video frame of the target video frame.

公开(公告)号：US20240404007A1

公开(公告)日：2024-12-05

申请号：US18696896

申请日：2022-10-27

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Hang DONG

IPC: G06T3/4053 ,  G06T5/73 ,  G06T7/246 ,  G06T7/33

Abstract: Embodiments of the present invention provide a video super-resolution method and apparatus, the method including: acquiring a first feature; processing the first feature by concatenated multistage residual dense blocks (RDBs) to obtain a fusion feature output by a RDB in each stage; for the fusion feature output by the RDB in each stage, aligning each of neighborhood features of the fusion feature with a target feature of the fusion feature to obtain an alignment feature corresponding to the RDB that outputs the fusion feature; and generating a super-resolution video frame corresponding to the target video frame on the basis of the alignment feature corresponding to the RDB in each stage and the initial feature of the target video frame.

公开(公告)号：US20250061686A1

公开(公告)日：2025-02-20

申请号：US18725661

申请日：2022-12-27

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Hang DONG

IPC: G06V10/52 ,  G06V10/77 ,  G06V10/80 ,  G06V10/82

Abstract: Embodiments of the present disclosure relate to the technical field of image processing, and provide an image processing method and apparatus. The method includes: respectively performing feature extraction on an image to be processed from a plurality of different spatial scales to obtain a target feature and at least one feature to be fused; fusing the target feature and the at least one feature to be fused to obtain a first feature; extracting a high-frequency feature and a low-frequency feature from the target feature; processing the high-frequency feature on the basis of a residual dense block (RDB) to obtain a second feature; fusing the low-frequency feature and the at least one feature to be fused to obtain a third feature; combining the first feature, the second feature and the third feature to obtain a fused feature; and processing the image to be processed on the basis of the fused feature.