Abstract: A method for generating a super-resolution image and related device is provided. In one aspect, the method comprises: receiving a first low-resolution image and a second low-resolution image, the first low-resolution image and second low-resolution image have a first spatial resolution and having been captured simultaneously by a pair of pixel arrays of a common image sensor, wherein the pixel arrays of the image sensor are located as to be diagonally shifted from each other by a sub-pixel increment; adaptively enhancing the first low-resolution and the second low-resolution images to generate an enhanced first low-resolution image and an enhanced second low-resolution image, respectively; mapping (e.g.

Abstract: An inference system trains and performs inference using a sparse neural network. The sparse neural network may include one or more layers, and each layer may be associated with a set of sparse weights that represent sparse connections between nodes of a layer and nodes of a previous layer. A layer output may be generated by applying the set of sparse weights associated with the layer to the layer output of a previous layer. Moreover, the one or more layers of the sparse neural network may generate sparse layer outputs. By using sparse representations of weights and layer outputs, robustness and stability of the neural network can be significantly improved, while maintaining competitive accuracy.

Abstract: The present disclosure is directed encoding LIDAR point cloud data. In particular, a computing system can receive point cloud data for a three-dimensional space. The computing system can generate a tree-based data structure from the point cloud data, the tree-based data structure comprising a plurality of nodes. The computing system can generate a serial representation of the tree-based data structure. The computing system can, for each respective node represented by a symbol in the serial representation: determine contextual information for the respective node, generate, using the contextual information as input to a machine-learned model, a statistical distribution associated with the respective node, and generate a compressed representation of the symbol associated with the respective node by encoding the symbol using the statistical distribution for the respective node.

Abstract: The present technique provides a first terminal device for exchanging signals with a wireless telecommunications network and a plurality of second terminal devices, the first terminal device configured to exchange signals with each of the plurality of second terminal devices, when the first terminal device provides a local cell for providing wireless connectivity for the plurality of second terminal devices, and to exchange signals with one or more infrastructure equipment of the wireless telecommunications network, and receive, from each of the plurality of second terminal devices served by the first terminal device when providing the local cell, suitability information indicative of the suitability of each of one or more other terminal devices or infrastructure equipment of the wireless telecommunications network to exchange signals with that second terminal device to provide for that second terminal devices another local cell.

Abstract: A method to compress an image includes assigning each pixel of the image to a cluster based on a red-green-blue (RGB) location of the pixel. The method also includes updating a centroid of the cluster after each pixel is assigned, based at least in part on the RGB location of the pixel, where the centroid is an RGB location. The method includes replacing each pixel in the image with an RGB value of the centroid of the cluster to which the pixel is assigned. The method also includes instructing a display to display a compressed image where, in the compressed image, each pixel in the image is replaced with the RGB value of the centroid of the cluster to which the pixel is assigned.

Abstract: A charging function (CHF) receives, from a policy control function (PCF), a first request for charging policy information for a packet data unit (PDU) session of a wireless device. The charging policy information is determined for the PDU session of the wireless device. The charging policy information indicates a charging method comprising one or more of: online charging; offline charging; and converged charging. A message comprising the charging policy information is sent to the PCF. The CHF receives from a session management function (SMF), a second request to establish a charging session. The second request comprises the charging method. A confirmation for the charging method is sent to the SMF.

Abstract: Provided are a content-adaptive binocular matching method and apparatus. The method includes: dividing both left and right images into grids so as to calculate feature information at grid points, and performing matching calculation between the left and right images at the grid points according to the feature information so as to determine points with high matching degrees as reference points; calculating parallax values of the reference points, determining an interlayer spacing, and layering all the reference points in a depth direction according to the parallax values and the interlayer spacing; for a non-reference point pixel in a certain image, determining a reference point closest to the non-reference point pixel, and determining a search range and the parallax value of the reference point; and performing matching calculation on the non-reference point pixel and a pixel in the search range in the other image.

Abstract: A touch-panel cellular phone specifies an invalid area not accepting a user's input operation on a touch panel in advance. The cellular phone detects a user's touch area on the touch panel so as to execute a function pre-assigned to the touch area not encompassed by the invalid area. Additionally, it is possible to reduce and display menu icons in the display area precluding the invalid area on the touch panel. Thus, it is possible to prevent an error operation when a user holding a cellular phone inadvertently touches the touch panel.

Abstract: Skin smoothing is applied to images using a bilateral filter and aided by a skin map. In one example a method includes receiving an image having pixels at an original resolution. The image is buffered. The image is downscaled from the original resolution to a lower resolution. A bilateral filter is applied to pixels of the downscaled image. The filtered pixels of the downscaled image are blended with pixels of the image having the original resolution, and the blended image is produced.

Abstract: One embodiment can provide a system for detecting occlusion at an orifice of a three-dimensional (3D) printer nozzle while the printer nozzle is jetting liquid droplets. During operation, the system uses one or more cameras to capture an image of the orifice of the printer nozzle while the 3D printer nozzle is jetting liquid droplets. The system performs an image-analysis operation on the captured image to identify occluded regions within the orifice of the 3D printer nozzle, compute an occlusion fraction based on the determined occluded regions, and generate an output based on the computed occlusion fraction, thereby facilitating effective maintenance of the 3D printer.

Abstract: An information processing method includes obtaining information on a deformation factor of a surface of a target substrate; obtaining a surface image of the target substrate; calculating a correction coefficient for correcting an image change due to deformation of the surface, based on the information on the deformation factor of the surface; and generating a corrected image of the target substrate by correcting the surface image of the target substrate using the correction coefficient.

Abstract: Embodiments include methods for image compression and decompression. A sending computing device may determine a type of packing used for a chunk of image data, generate metadata describing the type of packing used for the chunk of image data, pack the chunk of image data according to the determined type of packing, and send the packed chunk of image data and the metadata to a second computing device. A receiving computing device may decode the metadata describing the type of packing used for the chunk of image data, determine the type of packing used for the chunk of image data based on the decoded metadata, and unpack the chunk of image data according to the determined type of packing used for the chunk of image data.

Abstract: A method controls a first motor vehicle. The method includes the steps of: i) receiving status data of a roadway section and a geographic position of the roadway section by the first motor vehicle, ii) sensing, as a function of the received status data, the roadway section by a surroundings sensor of the first motor vehicle, and in response thereto, iii) aligning the surroundings sensor with a particular roadway feature of the roadway section, and/or iv) adapting an evaluation of data of the surroundings sensor, and/or v) updating the status data and transmitting the updated status data.

Abstract: The present embodiments relate to a method and device. The method comprises obtaining at least one first point from at least one point of a point cloud by projecting said point of the point cloud onto a projection plane and obtaining at least one other point of the point cloud determined according to said at least one first point; determining and encoding at least one interpolation coding mode for said at least one first point based on at least one reconstructed point obtained from said at least one first point and at least one interpolation point defined by said at least one interpolation coding mode to approximate said at least one other point of the point cloud; and signaling said at least interpolation coding mode as values of image data.

Abstract: A method and system for training a neural network are herein provided. According to one embodiment, a method includes generating a first labelled dataset corresponding to a first modulation scheme and a second labelled dataset corresponding to a second modulation scheme, determining a first gradient of a cost function between a first neural network layer and a second neural network layer based on back-propagation using the first labelled dataset and the second labelled dataset, and determining a second gradient of the cost function between the second neural network layer and a first set of nodes of a third neural network layer based on back-propagation using the first labelled dataset. The first set of nodes of the third neural network layer correspond to a first plurality of detector classes associated with the first modulation scheme.

Abstract: Systems and methods are disclosed herein relating to wireless device behavior after rejection of a resume request triggered by a Radio Access Network (RAN) based Notification Area Update (RNAU) or upon cell reselection during resume. In some embodiments, a method of operation of a wireless device comprises transmitting, to a RAN node, a Radio Resource Control (RRC) resume request triggered by an RNAU and receiving, from the RAN node, an RRC resume reject message comprising a wait timer value in response to the RRC resume request. The method further comprises starting a wait timer initialized with the wait timer value and sending the RNAU when the wait timer has expired. Corresponding embodiments of a wireless device are also disclosed. Embodiments of a wireless device and methods of operation thereof related to the behavior of the wireless device upon performing a cell reselection during resume are also disclosed.

Abstract: Methods and devices for encoding a point cloud. A bit sequence signaling an occupancy pattern for sub-volumes of a volume is coded using binary entropy coding. Contexts may be based on neighbour configuration and a partial sequence of previously-coded bits of the bit sequence. A determination is made as to whether to apply a context reduction operation and, if so, the operation reduces the number of available contexts. Example context reduction operations include reducing neighbour configurations based on shielding by sub-volumes associated with previously-coded bits, special handling for empty neighbour configurations, and statistics-based context consolidation.

Abstract: This disclosure relates to a method of sequential machine learning of data sets and an apparatus thereof. The method may include generating a first machine learning model by generating a first feature space based on a first data set, generating first predictive label information based on the first feature space, performing machine learning on a relationship between the first data set and first label information related to a first data set, and performing machine learning on a relationship between the first predictive label information and the first feature space. The method may also include generating a second machine learning model based on the first machine learning model by generating a second feature space based on a second data set, generating second predictive label information based on the second feature space, and performing machine learning on a relationship between the second data set and a second label information.

Abstract: A pose estimation training system includes: a first model configured to generate a first 6 degrees of freedom (DoF) pose of a first camera that captured a first image from a first domain; a second model configured to generate a second 6 DoF pose of a second camera that captured a second image from a second domain, where the second domain is different than the first domain; a discriminator module configured to, based on first and second outputs from the first and second encoder modules, generate a discriminator output indicative of whether the first and second images are from the same domain; and a training control module configured to, based on the discriminator output, selectively adjust at least one weight value shared by the first model and the second model.

Abstract: In various examples, motifs, watermarks, and/or signature inputs are applied to a deep neural network (DNN) to detect faults in underlying hardware and/or software executing the DNN. Information corresponding to the motifs, watermarks, and/or signatures may be compared to the outputs of the DNN generated using the motifs, watermarks and/or signatures. When a the accuracy of the predictions are below a threshold, or do not correspond to the expected predictions of the DNN, the hardware and/or software may be determined to have a fault—such as a transient, an intermittent, or a permanent fault. Where a fault is determined, portions of the system that rely on the computations of the DNN may be shut down, or redundant systems may be used in place of the primary system. Where no fault is determined, the computations of the DNN may be relied upon by the system.