Sanechips Technology Co., Ltd.

Gree Electric Appliances, Inc. of Zhuhai

Zte Corporation

Harbin Institute of Technology, Shenzhen

Ke Xu

Dehui Kong

Fang Zhu

Qunbo Liu

Jing You

Longfei Li

Yi Ni

Jisong Ai

Yaopeng Rong

Xin Liu

Kai Yu

Ning Wang

Bin Han

Guoning Lu

Wei Yang

Hua Liu

Sheng Luo

Handong Xue

Chengqiang Liu

Zhongqiu Zhang

Degen Zhen

Yingsheng Fu

Xiao Zhang

Hong Yang Wang

Tao Wang

Mingzhu Dong

Fang Wang

Bo Huang

Hengqi Liu

Long Huang

Fu-Chun Zheng

Yan Xiang

Zhenjiang Zhao

Cong Ren

Yaodong Li

Jianjun Song

Chong Xiang

Shuai Jiao

Zhou Han

Limin He

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.

Image denoising method and apparatus, electronic device, and storage medium

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 (); 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 (), 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 ().

Method and apparatus for training image restoration model, electronic device, and computer-readable storage medium

Disclosed are a method and apparatus for labeling an object contour in a target image, a non-transitory computer-readable storage medium and an electronic device. The method for labeling an object contour in a target image includes acquiring a target image feature of a target image, inputting the target image feature into a target generator, and acquiring a target mask of the target image generated by the target generator, wherein the target mask is used for labeling a contour of the target object.

Method and apparatus for marking object outline in target image, and storage medium and electronic apparatus

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.

Image processing method and device, computer storage medium and terminal

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.

Video processing method, device and storage medium

The present disclosure discloses a video denoising method and device, and a computer-readable storage medium. The video denoising method includes: dividing each video frame in an input video frame sequence into sub-image blocks, and calculating a block variance of each of the sub-image blocks; calculating an average variance of the sub-image blocks in a current video frame according to the calculated block variances, determining a noise level of the current video frame according to the average variance, selecting a denoise strength and a noise characteristic curve that match the noise level; and denoising the current video frame according to the denoise strength and the noise characteristic curve.

Video denoising method and device, and computer readable storage medium

Disclosed are a coding management method and apparatus based on High Efficiency Video Coding (HEVC). The method includes: obtaining a calculated correlation result for a HEVC basic unit before and after division, the correlation result including a spatial correlation result for the basic unit before the division and N basic units generated after the division, and N being an integer greater than 1; and judging whether or not to perform the division on the basic unit according to the calculated correlation result.

Coding management method and apparatus based on high efficiency video coding

Provided are a method and apparatus for presenting image for a VR device, a device and a non-transitory computer-readable storage medium. The method for presenting image for a VR device includes steps of: acquiring input image data; establishing a correspondence between the input image data and output image data in a polar coordinate system, the polar coordinate system having a pole which is an intersection of a center of a field of view of the VR device and a display plane; obtaining image data to be presented according to the output image data; and presenting the image data to be presented on the basis of a convex lens.

Method and apparatus for presenting image for virtual reality device, device and non-transitory computer-readable storage medium

The disclosure discloses a method and a device for controlling cylinder switching of a compressor, a unit and an air conditioning system. The method includes: determining whether the compressor needs to perform cylinder switching; if so, adjusting current operating frequency according to a system pressure difference so that both the adjusted operating frequency and the system pressure difference meet a cylinder switching condition of the compressor; and controlling the compressor to perform cylinder switching. At the moment, the system pressure difference and the operation frequency are stable, and would not interfere the compressor's maintaining of the single-cylinder or double-cylinder operation state, which guarantees the energy efficiency of the unit where the compressor is located, and improves the use experience of a user.

Compressor cylinder switching control method and device, unit and air conditioning system

A method for controlling the power-on or power-off of an air conditioner is provided. The method includes the following steps: determining whether a variable capacity compressor of the air conditioner is in a standby single-cylinder operation state before starting the air conditioner, where the variable capacity compressor is configured to be switchable between a single-cylinder operation state and a dual-cylinder operation state; if so, starting the air conditioner; if not, switching the variable capacity compressor to the standby single-cylinder operation state, and then starting the air conditioner. With this control method, regardless of whether the air conditioner is shut down because the power supply of the unit is cut off or because a power-off signal is received, the air conditioner can be started in a single-cylinder operation state in the next startup, so that the operation state of the cylinder is always determined when starting the air conditioner.

Method for controlling power-on or power-off of air conditioner

A method and a device for controlling a capacity change of a compressor, and a smart home appliance. The method includes: determining whether a capacity of the compressor is required to be changed; if yes, determining an intermediate frequency; changing the capacity of the compressor while maintaining the operating frequency of the compressor at the intermediate frequency; and the maintaining the operating frequency of the compressor at the intermediate frequency reduces a sudden change in output of the compressor after the changing the capacity.

Method and device for controlling capacity change of compressor, and smart home appliance

An image reconstruction method, device and apparatus and non-transitory computer-readable storage medium are disclosed. The method may include: determining norms of convolution kernels of each convolutional layer of a deep neural network model; determining the convolution kernels with norms greater than or equal to a preset threshold in each convolutional layer to obtain a target convolution kernel set of each convolutional layer; processing an input image of each convolutional layer by using the convolution kernels in the target convolution kernel set of each convolutional layer respectively, to obtain a first image processing result; obtaining a second image processing result by performing interpolation on an initial image; and determining a fusion result according to the first image processing result and the second image processing result and reconstructing the initial image according to the fusion result.

Image reconstruction method and device, apparatus, and non-transitory computer-readable storage medium

Disclosed are a variable capacity compressor operation mode determination method and device, a variable capacity compressor and an air conditioner. The variable capacity compressor operation mode determination method includes: detecting a current value of a compressor at present as A1 before switching an operation mode of the compressor; detecting the current value of the compressor at present as A2 after switching the operation mode of the compressor and reaching a preset time; comparing A1 and A2, determining that the switching of the operation mode of the compressor is successful when a ratio relationship between A1 and A2 satisfies a preset condition, and determining that switching of the operation mode of the compressor is failed when the ratio relationship between A1 and A2 dissatisfies a preset condition.

Variable capacity compressor operation mode determination method and device, variable capacity compressor, and air conditioner

Embodiments of the present disclosure provide a beamforming method and device based on phase shifter switching control, and a system. The method includes: acquiring a channel vector of a channel of each of low-load terminals; acquiring, based on the channel vector, contribution degrees of phase shifters corresponding to the channel; sequentially changing a connected state of each of the phase shifters from closing to opening based on the contribution degrees of the phase shifters corresponding to the channel, calculating a to-be-processed signal-to-interference-plus-noise ratio (SINR) of the low-load terminal after changing the connected state of the phase shifter once, stopping to change the connected state of the phase shifter if the to-be-processed SINR meets a preset condition, and changing the connected state of the phase shifter meeting the preset condition to the closing.

Beamforming method and device based on phase shifter switching control, and system

A de-interlacing processing method, a de-interlacing processing device and a computer-readable storage medium are provided. The method includes acquiring image content characteristic information of a pixel point to be interpolated; and determining according to the image content characteristic information whether a de-interlacing algorithm based on motion adaptive or a de-interlacing algorithm based on motion compensation is adopted to perform de-interlacing processing.

Growing community of inventors

Guangdong, China

Ke Xu