Abstract: Disclosed are a loop filtering implementation method and apparatus, and a computer storage medium. The method comprises: obtaining an picture to be filtered, wherein the picture to be filtered is generated from an original picture during the video encoding of a video to be encoded, the video to be encoded comprises an original picture frame, and the original picture frame comprises the original picture; based on the picture to be filtered, separately obtaining at least two colour components of the picture to be filtered; determining the fusion information of the picture to be filtered, wherein the fusion information is obtained by fusing the at least two colour components; and based on the fusion information, performing loop filtering processing on the picture to be filtered to obtain at least one colour component subsequent to filtering the picture to be filtered.

Abstract: A system for determining the distance, D between an object and a base line B, which is a line between a first camera's and a second camera's centres. The system comprises a first camera, a second camera and a processing system configured to receive data from the first camera and the second camera and to determine the position of an object, wherein the first and second cameras are oriented with their optical axes an angle ? to the base line, wherein ? is substantially non-right angle.

Abstract: An image decoding method includes a step of deriving a modified transform coefficient, wherein the step of deriving the modified transform coefficient includes the steps of: deriving a first variable indicating whether the transform coefficient exists in an area excluding a DC location of the current block; parsing an LFNST index based on the derivation result; and deriving the modified transform coefficient based on the LFNST index and an LFNST matrix, and based on the fact that the current block is divided into a plurality of sub-partition blocks, the LFNST index can be parsed without deriving the first variable.

Abstract: Intraoral scanning systems configured to perform computer-implemented methods for identifying dental features. The methods may include engaging a trained machine learning network to identify one or more dental features in one or more regions of a patient's dentition. Each of the dental features may be present in at least one of multiple records. Each of the records may include multiple images of the patient's dentition and may be taken with a different imaging modality. The confidence score may be determined or adjusted using a 3D model of the patient's dentition. The confidence score may be determined or adjusted based on the region of the patient's dentition within each record. The methods may include displaying an indicator of each dental feature that has a confidence score that is above a threshold on the 3D model of the patient's dentition, and modifying the display as a user adjusts the threshold.

Abstract: Systems, methods, and computer program products for managing simulated environments are described. A simulated environment is accessed which represents a physical environment, and representations of objects are included, maintained, or removed in the simulated environment based on whether objects are represented in image data of the physical environment, and based on whether objects are occluded by other objects in the image data of the physical environment. Future occlusion can also be predicted based on motion paths of objects.

Abstract: A three-dimensional (3D) microscope includes various insertable components that facilitate multiple imaging and measurement capabilities. These capabilities include Nomarski imaging, polarized light imaging, quantitative differential interference contrast (q-DIC) imaging, motorized polarized light imaging, phase-shifting interferometry (PSI), and vertical-scanning interferometry (VSI).

Abstract: Embodiments are directed to perceiving scene features using event sensors and image sensors. Paths may be scanned across objects in a scene with one or more beams. Images of the scene may be captured with frame cameras. Events may be generated based on detection of beam reflections that correspond to the objects. Trajectories may be based on the paths and the events. A distribution of intensity associated with the trajectories may be determined based on the energy associated with the traces in the images. Centroids for the trajectories may be determined based on the distribution of the intensity of energy, a resolution of the frame cameras, or timestamps associated with the events. Enhanced trajectories may be generated based on the centroids such that the enhanced trajectories may be provided to a modeling engine that executes actions based on the enhanced trajectories and the objects.

Abstract: The present disclosure relates to a method of providing at least one image of at least one real object captured by at least one scene camera of a plurality of scene cameras mounted on a vehicle. The method includes: providing camera poses of respective scene cameras of the plurality of scene cameras relative to a reference coordinate system associated with the vehicle, providing user attention data related to a user captured by an information capturing device, providing at least one attention direction relative to the reference coordinate system from the user attention data, determining at least one of the scene cameras among the plurality of scene cameras according to the at least one attention direction and the respective camera pose of the at least one of the scene cameras, and providing at least one image of at least one real object captured by the at least one of the scene cameras.

Abstract: An example apparatus includes image processing circuitry to determine an uncovered region of a background image in a current video frame relative to the background image in a previous video frame, the uncovered region obscured in the previous video frame by a first foreground region of the previous video frame, and the uncovered region uncovered in the current video frame based on movement of a second foreground region in the current video frame relative to the first foreground region of the previous video frame, and encoder circuitry to generate an updated frame portion by encoding the second foreground region and dirty blocks of the background image corresponding to the uncovered region without encoding static blocks of the background image, the static blocks not corresponding to the uncovered region, and store the updated frame portion in the at least one memory.

Abstract: Measures are provided to encode a signal. An input frame (102) is received and down-sampled to obtain a down-sampled frame (103). The down-sampled frame (103) is passed to an encoding module (104) which encodes the down-sampled frame (103) to generate an encoded frame (105). A decoded frame is obtained from a decoding module (106) which generates the decoded frame by decoding the encoded frame (105). A set of residual data (113) is generated by taking a difference between the decoded frame and the down-sampled frame (103) and is encoded to generate a set of encoded residual data. The encoding comprises transforming the set of residual data into a transformed set of residual data. The set of encoded residual data is output to a decoder to enable the decoder to reconstruct the input frame. Measures are also provided to decode a signal.

Abstract: A generation apparatus includes following units. A first acquisition unit acquires a first virtual viewpoint image generated based on a plurality of images captured by a plurality of image capturing apparatuses, and a first virtual viewpoint in a three-dimensional space including an image capturing space captured by the plurality of image capturing apparatuses. A second acquisition unit acquires a second virtual viewpoint image generated based on the plurality of captured images, and a second virtual viewpoint arranged with respect to a predetermined surface in the three-dimensional space and the first virtual viewpoint. A generation unit generates a third virtual viewpoint image corresponding to the first virtual viewpoint and including an image indicating a state where an object in the image capturing space is reflected on the predetermined surface, based on the first virtual viewpoint image, and the second virtual viewpoint image.

Abstract: An image decoding method according to the present document may include the steps of: deriving the position of the final significant coefficient in the current block and transform coefficients for the current block on the basis of residual information; determining whether the index of a sub-block including the final significant coefficient is 0 and whether the position of the final significant coefficient in the sub-block is greater than 0; determining whether a significant coefficient exists in a second area excluding a first area at the upper left end of the current block; and parsing an LFNST index from a bitstream when the position of the final significant coefficient is determined to be greater than 0 in the sub-block in which the index is 0, and the significant coefficient does not exist in the second area.

Abstract: An image decoding method according to the present invention includes: a step for determining a reference sample line of a current block; a step for determining whether candidate intra-prediction modes identical to the intra-prediction mode of the current block exist; a step for deriving the intra-prediction mode of the current block on the basis of the determination; and a step for performing intra-prediction on the current block on the basis of the reference sample line and the intra-prediction mode. Here, at least one of the candidate intra prediction modes may be derived by adding or subtracting an offset to or from the maximum value among the intra-prediction mode of a neighboring block that is above the current block and the intra-prediction mode of a neighboring block that is to the left of the current block.

Abstract: A point cloud coding method, including: partitioning a point cloud, and determining a current coding block; determining a quantization parameter optimization enable identifier, a hierarchical level index, and a quantization parameter offset parameter of the current coding block; determining, according to the hierarchical level index and the quantization parameter offset parameter, a quantization step Qstep corresponding to a level of detail; and upon detecting that the quantization parameter optimization enable identifier is a first value, performing operations for one or more points included in the current coding block.

Abstract: An encoder encodes a video, and includes: circuitry; and memory coupled to the circuitry. Using the memory, the circuitry: obtains at least two items of prediction information for a first partition included in the video; derives at least one template from neighboring samples which neighbor the first partition; calculates at least two costs, using the at least one template and the at least two items of prediction information; using the at least two costs, (i) determines at least one splitting direction for the first partition or (ii) assigns one of the at least two items of prediction information to a second partition split from the first partition according to the splitting direction, and another thereof to a third partition split from the first partition according to the splitting direction; and encodes the first partition according to the splitting direction and the at least two items of prediction information.

Abstract: A video decoding method performed by a decoding apparatus according to the present disclosure includes deriving one of a plurality of cross-component linear model (CCLM) prediction mode as a CCLM prediction mode of the current chroma block, deriving a sample number of neighboring chroma samples of the current chroma block based on the CCLM prediction mode of the current chroma block, a size of the current chroma block, and a specific value; deriving the neighboring chroma samples of the sample number, calculating CCLM parameters based on the neighboring chroma samples and the down sampled neighboring luma samples, deriving prediction samples for the current chroma block based on the CCLM parameters and the down sampled luma samples and generating reconstructed samples for the current chroma block based on the prediction samples, wherein the specific value is derived as 2.

Abstract: A system and a method for high-speed dual-view band-limited illumination profilometry using temporally interlaced acquisition is disclosed. The method comprises using a projecting unit for projecting sinusoidal fringe patterns onto an object and capturing fringe patterns deformed by the object. A 3D image of the object is recovered pixel by pixel from partial images provided by a first camera and a second camera by locating a point in the images of the second camera that matches a selected pixel of the first camera. 3D coordinates and wrapped phase are then estimated based on a calibration of the cameras and determining an horizontal coordinate on the plane of a projector of the projecting unit based on a calibration of the projector, and using a wrapped phase value to recover a 3D point of 3D coordinates (x, y, z).

Abstract: A method of compressing feature data includes: receiving feature data; performing spatial down sampling on the received feature data by applying a pixel unshuffle operation; and performing channel reduction on the spatially down sampled feature data by applying a non-linear two dimensional convolution with an activation.

Abstract: A device for analyzing or inspecting a prepared portion of a power cable includes a cable gripping section to grip a portion of the power cable proximate to a prepared end of the power cable, where the cable end has been prepared by removing certain portions of the power cable so that it can properly accept an electrical or cable accessory, such as a splice or termination. The device also includes an imaging device holding section to hold an imaging device at a predetermined radial distance from the prepared cable end. In particular, the imaging device holding section is radially and axially adjustable in position. During inspection of the prepared cable end, the imaging device is fully rotated about the prepared cable end to acquire a 360 degree image of the prepared cable end.

Abstract: A method of encoding or decoding video data comprises: for each respective intra prediction mode of a plurality of intra prediction modes in a most-probable mode (MPM) list: generating, based on reference samples for a template region and using the respective intra prediction mode, prediction samples for the template region; and determining a cost for the respective intra prediction mode; determining a first intra prediction mode and a second intra prediction mode in the MPM list having lowest costs; determining a preliminary prediction block for the first intra prediction mode and a preliminary prediction block for the second intra prediction mode; generating a prediction block based on a fusion of the preliminary prediction blocks weighted according to a weight for the first intra prediction mode and a weight for the second intra prediction mode.