Abstract: The present disclosure provides methods for convolutional-neural-network (CNN) based filter for video coding. An exemplary method includes: applying motion estimation to a target coding block, to determine a reference block of the target coding block; inputting, to a convolutional neural network (CNN) filter, image data associated with the target coding block and the reference block; and executing the CNN filter to determine a residual associated with the target coding block based on the input image data.

Abstract: Methods and apparatuses are provided for processing video data. An exemplary method includes: decompressing a compressed frame to generate a key frame representing a face; generating, for the key frame, a first set of parameters associated with a 3-dimensional (3D) face representation of the face; reconstructing, for each of one or more inter frames, a second set of parameters associated with a 3D face representation of the face according to compressed inter-predicted residuals of the second set of parameters; and generating a video comprising the face based on the key frame, the first set of parameters, and the second set of parameters.

Abstract: Methods and apparatuses are provided for compressing video data based on keypoint features. An exemplary video compression method includes: receiving a video sequence; encoding one or more pictures of the video sequence; and generating a bitstream; wherein the encoding includes: representing a first picture by a first set of keypoints and a second set of keypoints, the second set comprising less keypoints than the first set; and compressing the video sequence based on the first set and second set of keypoints.

Abstract: Embodiments of the present disclosure provide method and apparatus for determining channel parameter. The determined channel parameter may be used for adaptive subband precoding. A method performed by a network device comprises determining at least one channel parameter for a subband related to a terminal device. The at least one channel parameter for the subband is calculated based on at least one channel parameter for a larger frequency band comprising the subband.

Abstract: The present disclosure provides methods and apparatuses for performing image synthesis. An exemplary image synthesis method includes: acquiring a first image and a second image an image quality of the first image being higher than an image quality of the second image; obtaining a compressed image by compressing the first image; and synthesizing at least a part of the compressed image with at least a part of the second image.

Abstract: The present disclosure provides pre-analysis based methods for adaptively compressing image data consumed by machine vision tasks. An exemplary method includes: receiving a video sequence; encoding one or more input pictures associated with the video sequence; and generating a bitstream, wherein the encoding includes: performing instance segmentation of an input picture, to generate one or more segment masks; combining the one or more segment masks to generate a merged mask; extracting, from the input picture, a region comprising the merged mask; and compressing image data representing the extracted region.

Abstract: An image data encoding method is provided. The image data encoding method includes receiving an input image and a quantization parameter (QP); performing pre-analysis of the input image based on the QP to obtain input image data for machine version; determining at least one of a temporal redundancy or a spatial redundancy of the input image data; determining, based on the at least one of temporal redundancy or spatial redundancy, whether to perform at least one of temporal down-sampling or spatial down-sampling; performing down-sampling of the input image data according to the determination, wherein the down-sampling includes at least one of temporal down-sampling or spatial down-sampling; and encoding the down-sampled image data based on the QP.

Abstract: There is provided mechanisms for precoded transmission of data. A method is performed by a network node. The method comprises obtaining an indication that a CSI report as received from a user equipment served by the network node is of a quality below a quality threshold. The method comprises, in response thereto, transmitting, whilst applying at least one precoder, data towards the user equipment. The at least one precoder is a function of at least one CSI value reported from the user equipment earlier than the CSI report with quality being below the quality threshold was received.

Abstract: A method, network node and wireless device in a wireless communication system for one of transmitting and receiving a phase-tracking reference signal, PT-RS. The method includes obtaining information about a position in a time domain of a scheduled first demodulation reference signal, DM-RS, in a slot, and one of transmitting and receiving the PT-RS within the slot, the position of the PT-RS depending on the position in the time domain of the scheduled first DM-RS.

Abstract: Embodiments of the present disclosure relates to the field of solar cells, and in particular to a solar cell and a production method thereof, and a photovoltaic module. The solar cell includes: a P-type emitter formed on a first surface of an N-type substrate and including a first portion and a second portion, a top surface of the first portion includes first pyramid structures, and a top surface of the second portion includes second pyramid structures whose edges are straight. A transition surface is respectively formed on at least one edge of each first pyramid structure, and each of top surfaces of at least a part of the first pyramid structures includes a spherical or spherical-like substructure. A tunnel layer and a doped conductive layer sequentially formed over a second surface of the N-type substrate. The present disclosure can improve the photoelectric conversion performance of solar cells.

Abstract: A photovoltaic cell is provided, including a substrate having a front surface with metal and non-metal pattern regions, first and second pyramid structures in each metal pattern region, third and fourth pyramid structures in each non-metal pattern region, a first tunneling layer and a first doped conductive layer on a portion of the front surface in a respective metal pattern region, and a second tunneling layer and a second doped conductive layer on a rear surface of the substrate. A dimension of a bottom portion of each first pyramid structure is greater than that of each second pyramid structure. A dimension of a bottom portion of each third pyramid structure is greater than that of each fourth pyramid structure. An area proportion of the first pyramid structures in the metal pattern region is greater than that of the third pyramid structures in a respective non-metal pattern region.

Abstract: A photovoltaic cell is provided, including a substrate having a front surface with metal and non-metal pattern regions, first and second pyramid structures in each metal pattern region, third and fourth pyramid structures in each non-metal pattern region, a first tunneling layer and a first doped conductive layer on a portion of the front surface in a respective metal pattern region, and a second tunneling layer and a second doped conductive layer on a rear surface of the substrate. A dimension of a bottom portion of each first pyramid structure is greater than that of each second pyramid structure. A dimension of a bottom portion of each third pyramid structure is greater than that of each fourth pyramid structure. An area proportion of the first pyramid structures in the metal pattern region is greater than that of the third pyramid structures in a respective non-metal pattern region.

Abstract: A photovoltaic cell is provided, including a substrate having a front surface with metal pattern regions and a rear surface, first pyramid structures in each metal pattern region, platform protrusion structures on the rear surface, a first tunneling layer and a first doped conductive layer on a portion of the front surface in a respective metal pattern region, and a second tunneling layer and a second doped conductive layer on the rear surface. A height of each first pyramid structure is greater than that of each platform protrusion structure. A one-dimensional dimension of a bottom portion of each first pyramid structure is less than that of each platform protrusion structure. A doping element type of the first doped conductive layer is the same as that of the substrate. A doping element type of the second doped conductive layer is different from that of the first doped conductive layer.

Abstract: Embodiments of the present disclosure relates to the field of solar cells, and in particular to a solar cell and a photovoltaic module. The solar cell includes: a substrate having a front surface and a rear surface; a first tunnel layer and a first doped conductive layer sequentially formed over the front surface of the substrate, the first tunnel layer and the first doped conductive layer are each aligned with a metal pattern region on the front surface; and a second tunnel layer and a second doped conductive layer sequentially formed over the rear surface of the substrate, and in a respective Raman spectrum, a full width at half maximum corresponding to the first doped conductive layer is not greater than a full width at half maximum corresponding to the second doped conductive layer.

Abstract: A photovoltaic cell is provided, including a substrate having a front surface with metal and non-metal pattern regions, first and second pyramid structures in each metal pattern region, third and fourth pyramid structures in each non-metal pattern region, a first tunneling layer and a first doped conductive layer on a portion of the front surface in a respective metal pattern region, and a second tunneling layer and a second doped conductive layer on a rear surface of the substrate. A dimension of a bottom portion of each first pyramid structure is greater than that of each second pyramid structure. A dimension of a bottom portion of each third pyramid structure is greater than that of each fourth pyramid structure. An area proportion of the first pyramid structures in the metal pattern region is greater than that of the third pyramid structures in a respective non-metal pattern region.

Abstract: Provided are method and system of calculating cross-section area and included angle of three-dimensional blood vessel branch, comprising: obtaining the contours of a main blood vessel and a branch blood vessel; determining connecting points of the main blood vessel and the branch blood vessel, a three-dimensional branch outer contour, and an initial normal vector of a branch section; determining the position of the branch section at the branch connecting part and an intersecting cross-section of the branch section and the branch outer contour; rotating the three-dimensional branch cross-section contour to obtain an equivalent two-dimensional branch cross-section contour, and calculating the area of the two-dimensional branch cross-section contour; obtaining branch cross-section areas and corresponding normal vectors thereof; and taking the minimum branch cross-section area as the cross-section area of this segment of branch blood vessel, and determining the included angle between the branch blood vessel and t

Abstract: A travel plan generation device according to an aspect of the present invention is provided with a generation unit that generates a travel plan for traveling a plurality of points by a plurality of mobile bodies by performing, at each output step, processing of selecting any one point out of the plurality of points and any one mobile body out of the plurality of mobile bodies by using a recurrent neural network configured to output visiting probabilities at the plurality of points and use probabilities of the plurality of mobile bodies when point information regarding the plurality of points and mobile body information regarding the plurality of mobile bodies are input, and an output unit that outputs the travel plan.

Abstract: A method performed by a network node for creating a precoder for forming a Downlink, DL, beam between the network node and a User Equipment, UE, which DL beam is for reciprocity-based Multiple Input Multiple Output, MIMO, communication in a wireless communications network is provided. The network node obtains matched filter channel estimates for an Uplink, UL, signal, based on a reference signal from the UE known by the network node. The network node obtains a hypothesis testing space within a first precoder codebook, of one polarization, based on the matched filter channel estimates. The network node selects a set of precoder candidates out of the first precoder codebook in accordance with the hypotheses testing space. The network node creates the precoder for forming the DL beam between the network node and the UE, based on calculating a linear combination of the precoder candidates in the set of precoder candidates.

Abstract: The present disclosure provides methods for convolutional-neural-network (CNN) based filter for video coding. An exemplary method includes: applying motion estimation to a target coding block, to determine a reference block of the target coding block; inputting, to a convolutional neural network (CNN) filter, image data associated with the target coding block and the reference block; and executing the CNN filter to determine a residual associated with the target coding block based on the input image data.

Abstract: A configuration helper system (CHS) is described that simplifies the task of generating configuration information for a customer premises equipment (CPE) in a customer's on-premise network to enable the CPE to communicate with the customer's cloud network over a particular communication channel. The CHS is configured to generate configuration information that is customized for the particular CPE and communication channel. Given information about the CPE and the communication channel, the CHS automatically identifies a particular set of configuration parameters to be included in the customized configuration information and determines values for the set of parameters, where some of the values may be provided by the customer. A particular CPE-specific format is determined for the configuration information.