公开(公告)号：US20250069188A1

公开(公告)日：2025-02-27

申请号：US18721427

申请日：2022-02-28

Applicant: SANECHIPS TECHNOLOGY CO.,LTD

Inventor： Yan XIANG ,  Dehui KONG ,  Ke XU

IPC: G06T3/4046 ,  G06T3/4053

Abstract: Provided in the embodiments of the present disclosure are a method and apparatus for training an image reconstruction model, a storage medium, and an electronic device. The method includes: acquiring a target teacher image reconstruction model; training, by using the target sample image set, a student image reconstruction model to be trained, and ending the training until a target loss value satisfies a second preset loss condition, so as to obtain a target student image reconstruction model, wherein the target loss value is a loss value determined according to a first loss value and a second loss value, and the second loss value is a loss value determined according to a difference value between a predicted value and a real value respectively determined by the student image reconstruction model to be trained and the target teacher image reconstruction model.

公开(公告)号：US20230196721A1

公开(公告)日：2023-06-22

申请号：US17999467

申请日：2021-06-09

Applicant: SANECHIPS TECHNOLOGY CO., LTD.

Inventor： Cong REN ,  Ke XU ,  Dehui KONG ,  Jing YOU ,  Xin LIU ,  Fang ZHU

IPC: G06V10/60 ,  G06T3/00 ,  G06T3/40 ,  G06V10/24 ,  H04N19/513

CPC classification number: G06V10/60 ,  G06T3/40 ,  G06T3/0093 ,  G06V10/24 ,  H04N19/513

Abstract: A low-illuminance video processing method, a low-illuminance video processing device and a storage medium are disclosed. The method includes: acquiring a same number of preceding frame images and subsequent frame images corresponding to a current video frame of a low-illuminance video to obtain a frame image set corresponding to the current video frame, and performing traversal on the low-illuminance video to obtain frame image sets corresponding to all video frames; after performing image alignment on all frame images in the frame image sets corresponding to all video frames, inputting the frame image sets into a pre-trained low-illuminance image enhancement model to obtain enhanced frame images; and generating an enhanced video based on the enhanced frame images.

公开(公告)号：US20240411555A1

公开(公告)日：2024-12-12

申请号：US18717053

申请日：2022-12-05

Applicant: SANECHIPS TECHNOLOGY CO., LTD.

Inventor： Hong LEI ,  Degen ZHEN ,  Tongqing WU ,  Dehui KONG ,  Ke XU

IPC: G06F9/30

Abstract: There are provided a vector operation method, a vector operator, an electronic device, and a computer-readable storage medium. The vector operation method includes: splitting a target vector operation to be performed to determine a plurality of basic operations in a predetermined execution order; sequentially generating, according to the predetermined execution order, a plurality of basic operation instructions corresponding to the plurality of basic operations; and sequentially executing, according to the predetermined execution order, the plurality of basic operation instructions on initial data to be subjected to the target vector operation, so as to implement the target vector operation on the initial data, wherein in two adjacent basic operations, to-be-calculated data for a latter basic operation is an operation result of a former basic operation.

公开(公告)号：US20240394836A1

公开(公告)日：2024-11-28

申请号：US18694974

申请日：2022-03-16

Applicant: SANECHIPS TECHNOLOGY CO., LTD.

Inventor： Cong REN ,  Hengqi LIU ,  Ke XU ,  Dehui KONG ,  Jisong AI ,  Xin LIU ,  Jing YOU

IPC: G06T5/20

Abstract: The present disclosure provides a method for training an image enhancement model, the image enhancement model includes an enhancement module including convolution branches corresponding to brightness intervals; and the method includes: inputting a sample image to the image enhancement model, and acquire a result image output by the image enhancement model; calculating losses including an image loss of the result image relative to a Ground Truth image, and a first constraint loss of brightness histogram constraint of each of the convolution branches of an image output from each of the convolution branches relative to the Ground Truth image; adjusting the enhancement module according to the losses; and in a case where a training end condition is not met, returning to the operation of inputting the sample image to the image enhancement model. The present disclosure further provides an image enhancement method and a computer-readable medium.

公开(公告)号：US20230269395A1

公开(公告)日：2023-08-24

申请号：US18010356

申请日：2021-06-01

Applicant: SANECHIPS TECHNOLOGY CO., LTD.

Inventor： Wei YANG ,  Ke XU ,  Dehui KONG ,  Jianjun SONG ,  Fang ZHU

IPC: H04N19/59 ,  G06T5/50 ,  G06T7/11 ,  H04N19/51

CPC classification number: H04N19/59 ,  G06T5/50 ,  G06T7/11 ,  H04N19/51 ,  G06T2207/20221

Abstract: The present application provides a video processing method, a device, and a storage medium. The method includes: coding and decoding an original video to obtain a mixed resolution video, where the mixed resolution video includes a first resolution frame and a second resolution frame each corresponding to a key frame, and a third resolution frame corresponding to a non-key frame, where the first resolution frame has a resolution higher than a resolution of the second resolution frame or a resolution of the third resolution frame; and amplifying, according to the first resolution frame and the second resolution frame, the third resolution frame corresponding to the non-key frame to output an amplified video, where the amplified video includes the first resolution frame corresponding to the key frame, and an amplified target frame corresponding to the non-key frame.

公开(公告)号：US20230230206A1

公开(公告)日：2023-07-20

申请号：US17921271

申请日：2021-04-22

Applicant: SANECHIPS TECHNOLOGY CO., LTD.

Inventor： Jisong AI ,  Ke XU ,  Dehui KONG ,  Ning WANG ,  Xin LIU ,  Jing YOU ,  Fang ZHU

IPC: G06T5/00 ,  G06T5/20

CPC classification number: G06T5/002 ,  G06T5/20 ,  G06T2207/20081

Abstract: The present application relates to the field of image processing, and provides an image denoising method and apparatus, an electronic device and a storage medium. The image denoising method includes: acquiring an image to be processed, and inputting the image to be processed into an image denoising model to acquire a denoised image, wherein the image denoising model is a model formed by combining a U-shaped network, a residual network and a dense network.

公开(公告)号：US20220245761A1

公开(公告)日：2022-08-04

申请号：US17618534

申请日：2020-04-16

Applicant: SANECHIPS TECHNOLOGY CO., LTD

Inventor： Dehui KONG ,  Ke XU ,  Xiao ZHANG ,  Hong WANG ,  Bin HAN ,  Ning WANG ,  Xin LIU ,  Guoning LU ,  Fang ZHU

IPC: G06T3/40

Abstract: The present application provides an image processing method, an image processing device, a computer storage medium and a terminal, the image processing method includes: determining convolution kernels of at least two sizes for feature extraction; performing sparsity constraint for the determined convolution kernels of at least two sizes for feature extraction through a preset objective function; and performing feature extraction on an image based on the convolution kernels subjected to the sparsity constraint.

公开(公告)号：US20230177650A1

公开(公告)日：2023-06-08

申请号：US17924158

申请日：2021-05-06

Applicant: SANECHIPS TECHNOLOGY CO., LTD.

Inventor： Jing YOU ,  Hengqi LIU ,  Ke XU ,  Dehui KONG ,  Jisong AI ,  Xin LIU ,  Cong REN

IPC: G06T5/00 ,  G06T3/40

CPC classification number: G06T5/001 ,  G06T3/40 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Disclosed are a method and apparatus for training an image restoration model, an electronic device, and a computer-readable storage medium. The method for training an image restoration model includes: pre-processing training images to obtain a low-illumination image sample set (110); determining, based on low-illumination image samples in the low-illumination image sample set and the image restoration model, a weight coefficient of the image restoration model (120), wherein the image restoration model is a neural network model determined on a U-Net network and a deep residual network; and adjusting the image restoration model according to the weight coefficient, and further training the adjusted image restoration model using the low-illumination image samples until the image restoration model restores parameters of all the low-illumination image samples in the low-illumination image sample set into a preset range (130).