Abstract: This application relates to a method and a system for compressing a captured image of an item such as a mailpiece or parcel. The system may include a memory configured to store images of a plurality of items captured while the items are being transported and a processor in data communication with the memory. The processor may be configured to receive or retrieve one or more of the captured images, perform a wavelet scattering transform on the one or more captured images, perform deep learning on the wavelet scattering transformed images to classify the wavelet scattering transformed images and compress the classified wavelet scattering transformed images. Various embodiments can significantly improve a compression efficiency, a communication efficiency of compressed data and save a memory space so that the functionality of computing devices is significantly improved.

Abstract: Techniques are described for pre-processing frames to apply a temporal filter. A P-frame may be temporally filtered based on neighboring reference frames. The temporal filter may be applied to blocks of the P-frame to improve alignment with dependent frames that are encoded based on blocks of the P-frame.

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: An electronic device is provided.

Abstract: An image processing device for use in an image encoder and/or an image decoder, for deblocking a block edge between a first block and a second block of an image encoded with a block code, is provided. The image processing device comprises a filter for filtering the block edge, configured to, for at least some of the pixels to be filtered, within a deblocking range from the block edge, the deblocking range being perpendicular to the block edge, determine a filtered pixel value from an original pixel value of the pixel and at least one further pixel value, determine a clipping value of the pixel, dependent upon a distance of the pixel from the block edge, and clip the filtered pixel value, using the clipping value resulting in a deblocked pixel value.

Abstract: This invention predicts that intra mode prediction is more effective for the macroblocks where motion estimation in inter mode prediction fails. This failure is indicated by a large value of the inter mode SAD. This invention performs intra mode prediction for only macro blocks have larger inter mode SADs. The definition of a large inter mode SAD differs for different content. This invention compares the inter mode SAD of a current macroblock with an adaptive threshold. This adaptive threshold depends on the average and variance of the SADs of the previous predicted frame. An adaptive threshold is calculated for each new predictive frame.

Abstract: An image processing method and apparatus, a device, a video processing method and a storage medium are provided. The image processing method includes: receiving an input image; and processing the input image by using the convolutional neural network to obtain an output image. A definition of the output image is higher than a definition of the input image. Processing the input image by using the convolutional neural network to obtain the output image includes: performing feature extraction on the input image; concatenating the input image and the plurality of first images; performing the feature extraction on the first image group; fusing the plurality of second images and the plurality of first images; concatenating the input image and the plurality of third images to obtain a second image group; and performing the feature extraction on the second image group to obtain the output image.

Abstract: In one embodiment, a method includes determining a gaze direction of a user wearing a head-mounted device, the head-mounted device having a display configured to output an image having multiple of pixels. The method may further include determining, for each of the multiple pixels, a set of sampling locations based on the gaze direction of the user, the sets of sampling locations of the multiple pixels being a portion of a sampling pattern defined based on the gaze direction of the user. In one embodiment, the method may also include computing, for each of the multiple pixels, a color value for the pixel by sampling a scene according to the set of sampling locations associated with the pixel, generating the image using the color values of the multiple pixels, and outputting the image using the display of the head-mounted device.

Abstract: Disclosed is a method and an apparatus for backlight control and a display device. The apparatus comprises: a block brightness module for calculating an initial brightness value of each backlight block in a backlight source according to initial image data; a filtering module for performing spatial filtering and temporal filtering on the initial brightness value of each backlight block to obtain an adjusted brightness value of each backlight block; a control module for generating a brightness control signal according to the adjusted brightness value of each backlight block to adjust brightness of the backlight source. An intermediate brightness value of each backlight block is no less than the initial brightness value of that backlight block. Based on backlight adjustment for reducing power consumption, display effect reduction on a portion of image due to uneven brightness of the portion of the image during the spatial filtering is avoided.

Abstract: Examples described herein relate to a system that after decoding of video by the first device, provides a memory address of decoded video in the memory device to a second driver for a second device and perform a second device driver that causes the second device to access the decoded video directly from a translation of the memory address of the memory device, wherein the second device is to access the decoded video with memory properties of the decoded video and decompression information of the decoded video. In some examples, the first device comprises one or more of: a graphics processing unit integrated with a central processing unit (CPU), a discrete graphics processing unit, or a video decoder accelerator. In some examples, the second device comprises one or more of: a graphics processing unit integrated with a central processing unit (CPU) or a discrete graphics processing unit. In some examples, the memory properties of the decoded video comprise swizzle information.

Abstract: An example method of video processing includes determining, for a conversion between a current video unit of a video and a bitstream representation of the video, availability of one or more samples in a first neighboring region of the current block for a coding process of the conversion independently from information of a second neighboring region of the current block. The second neighboring region is adjacent to the first neighboring region, and the one or more samples are padded in case determined to be unavailable. The method includes performing the conversion based on the determining.

Abstract: Aspects of the disclosure provide methods and apparatuses for video encoding/decoding. In some examples, an apparatus for video decoding includes processing circuitry. The processing circuitry reconstructs a first sample in a video of a coded video bitstream based on a non-linear mapping based filter with a first filter shape configuration of a plurality of filter shape configurations. The plurality of filter shape configurations including at least two filter shape configurations that are based on a same geometric shape. The processing circuitry determines a switch from the first filter shape configuration to a second filter shape configuration. The processing circuitry reconstructs a second sample in the video based on the non-linear mapping based filter with the second filter shape configuration.

Abstract: The refinement of block-based predictive coding and decoding of pictures as applicable in, e.g., hybrid video codecs, using additional reconstructed samples or residuals is described. An apparatus for block-based predictive decoding of a picture is described. The apparatus includes a combiner configured to combine a residual signal a predetermined block of the picture and a reference signal for the predetermined block so as to obtain a first spectrum, the residual signal correcting a prediction error of a prediction of the predetermined block of the picture; a reducer configured to perform thresholding on the first spectrum to obtain a second spectrum so that coefficients below a threshold value are set to a predefined value; an extractor configured to obtain from the second spectrum a modified version of the residual signal; and a reconstructor block configured to decode the predetermined block of the picture from the data stream on the basis of the modified version of the residual signal.

Abstract: Aspects of the disclosure include methods, apparatuses, and non-transitory computer-readable storage mediums for video encoding/decoding. An apparatus includes processing circuitry that decodes prediction information of a current block that is a part of a current picture in a video bitstream. The prediction information indicates a reference block for the current block. The processing circuitry generates filter coefficients of a filter operation based on neighboring reconstructed samples of the current block and neighboring reconstructed samples of the reference block that are co-located with the neighboring reconstructed samples of the current block. The filter operation compensates local changes to the current picture, such as illumination change or motion blur. The processing circuitry determines a prediction block for the current block based on the filter operation being performed on the reference block of the current block.

Abstract: A method of preprocessing incoming video data of at least one region of interest from a camera collecting video data having a first field of view is disclosed herein that includes receiving the incoming video data from the camera; preprocessing the incoming video data, by a computer processor, according to preprocessing parameters defined within a runtime configuration file, with the preprocessing including formatting the incoming video data to create first video data of a first region of interest with a second field of view that is less than the first field of view; and publishing the first video data of the first region of interest to an endpoint to allow access by a first subscriber.

Abstract: An image processing method includes the following steps. Firstly, a block-size value is obtained. Then, a first frame into a plurality of first blocks according to the block-size value is divided. Then, a second frame into a plurality of second blocks according to the block-size value is divided. Then, a noise reduction intensity array is obtained according to a first pixel information of each first block and a second pixel information of each second block. Then, an output frame is obtained according to the noise reduction intensity array, the first frame and the second frame.

Abstract: A method includes receiving a bit stream; determining, using the bit stream, whether an adaptive resolution management mode is enabled; determining, using the bit stream, a scaling factor including a vertical scaling constant component and a horizontal scaling constant component; and reconstructing pixel data of a current block in adaptive resolution management mode and using the determined scaling factor, the reconstructing including scaling the current block horizontally by the horizontal scaling constant component and scaling the current block vertically by the vertical scaling constant component. Related apparatus, systems, techniques and articles are also described.

Abstract: A display device includes a display unit including gate lines and pixels electrically coupled to the gate lines; a timing controller configured to generate an on-clock signal, an off-clock signal, an enable signal, and a common signal; a clock generator configured to generate a plurality of clock signals having different phases based on the on-clock signal and the off-clock signal, when the enable signal has a first voltage level, wherein the clock generator is to insert a common pulse into each of the plurality of clock signals based on the common signal, when the enable signal has a second voltage level different from the first voltage level; and a gate driver configured to generate gate signals based on the plurality of clock signals, and to sequentially provide the gate signals to the gate lines.

Abstract: In a decoding method performed by a decoding apparatus according to embodiments of the present document, whether signaling of information related to virtual boundaries is present in a sequence parameter set (SPS) or picture header information may be determined based on a virtual boundaries enabled flag.

Abstract: An encoder includes circuitry and memory coupled to the circuitry. In operation, the circuitry: encodes information for deriving a parameter into a header of a bitstream; filters reconstructed samples in a first image using a filtering process, to generate a second image; determines whether the parameter has a predefined value; encodes a third image using the second image when the parameter has the predefined value; and encodes the third image using the first image when the parameter does not have the predefined value.

Abstract: Disclosed is an information processing device, comprising: acquisition circuitry configured to acquire image data including a frame; and index calculation circuitry configured to: determine an average value of the frame, and predict a signal-to-noise ratio of the image data based on the average value of the frame.

Abstract: A video encoder or video decoder are configured to reconstruct the video data to generate reconstructed video data. The video encoder or video decoder may further perform a plurality of loop filter operations on the reconstructed video data in parallel, wherein the plurality of loop filter operations includes a first filter operation that is not a bilateral filter operation or a sample adaptive offset (SAO) filter operation, and perform a joint clipping operation on a first output of the first filter and a second output of a second loop filter operation of the plurality of loop filter operations. The first filter operation may be a cross-component sample adaptive offset (CCSAO) filter operation.

Abstract: Techniques are provided herein for processing video data. The techniques include identifying one or more input factors including one or more of signal quality factors, video content complexity factors, and hardware buffering factors for one or more of a video encoding system and a video playback system; evaluating the one or more input factors to determine adjustments to apply to one or both of the video encoding system and the video playback system; and applying the determine adjustments to the one or both of the video encoding system and the video playback system.

Abstract: A method of controlling an Adaptive Loop Filter for one or more image portions of an image, the method comprising controlling filtering on a first sample of an image portion based on one or more neighbouring sample value(s) of the first sample value, wherein the controlling uses a nonlinear function which has one or more variables based on one or more of the neighbouring sample value(s).

Abstract: Provided is a video decoding method of applying a deblocking filter to neighboring pixels adjacent to a boundary of a current block, the video decoding method including selecting a deblocking filter to be applied to the neighboring pixels from among a plurality of deblocking filters according to pixel values of the neighboring pixels and a size of the current block, and applying the selected deblocking filter to the neighboring pixels, wherein the plurality of deblocking filters include three or more deblocking filters having different ranges of neighboring pixels to which deblocking filtering is applied.

Abstract: Provided is a video decoding method of applying a deblocking filter to neighboring pixels adjacent to a boundary of a current block, the video decoding method including selecting a deblocking filter to be applied to the neighboring pixels from among a plurality of deblocking filters according to pixel values of the neighboring pixels and a size of the current block, and applying the selected deblocking filter to the neighboring pixels, wherein the plurality of deblocking filters include three or more deblocking filters having different ranges of neighboring pixels to which deblocking filtering is applied.

Abstract: The present invention relates to image processing, and more particularly, to a video coding/decoding method using a clipped motion vector and an apparatus thereof. An embodiment of the present invention relates to a method of decoding an image. The method includes clipping a motion vector of a reference picture in a predetermined dynamic range to generate a clipped motion vector, storing the clipped motion vector in a buffer, deriving a motion vector of a coding treeblock using the motion vector stored in the buffer, and performing inter prediction decoding process using the motion vector of the coding treeblock. According to the exemplary embodiment of the present invention, a size of a memory required for storing motion vectors may be reduced.

Abstract: Provided is a video decoding method of applying a deblocking filter to neighboring pixels adjacent to a boundary of a current block, the video decoding method including selecting a deblocking filter to be applied to the neighboring pixels from among a plurality of deblocking filters according to pixel values of the neighboring pixels and a size of the current block, and applying the selected deblocking filter to the neighboring pixels, wherein the plurality of deblocking filters include three or more deblocking filters having different ranges of neighboring pixels to which deblocking filtering is applied.

Abstract: Provided is a video decoding method of applying a deblocking filter to neighboring pixels adjacent to a boundary of a current block, the video decoding method including selecting a deblocking filter to be applied to the neighboring pixels from among a plurality of deblocking filters according to pixel values of the neighboring pixels and a size of the current block, and applying the selected deblocking filter to the neighboring pixels, wherein the plurality of deblocking filters include three or more deblocking filters having different ranges of neighboring pixels to which deblocking filtering is applied.

Abstract: A method of decoding a motion vector includes: obtaining information indicating a motion vector resolution (MVR) of a current block from a bitstream, selecting one candidate block from among at least one candidate block, based on the MVR of the current block; and obtaining a motion vector of the current block corresponding to the MVR, by using a motion vector of the determined one candidate block as a prediction motion vector of the current block.

Abstract: A method for adaptive loop filtering is provided that includes determining a coefficient value for each coefficient position of an adaptive loop filter, applying the adaptive loop filter to at least a portion of a reconstructed picture using the coefficient values, and entropy encoding coefficient values into a compressed bit stream using predetermined short binary codes, wherein the short binary code used depends on the coefficient position of the coefficient value.

Abstract: An electronic apparatus is disclosed. The electronic apparatus includes: a memory storing an input image, and a processor configured to: apply a filter to the input image to identify the input image as a plurality of areas, apply a first low-frequency filter to a first area among the plurality of areas, and apply a second low-frequency filter to a second area among the plurality of areas to perform downscaling, wherein a cut-off frequency of the second low-frequency filter is configured to be higher than a cut-off frequency of the first low-frequency filter.

Abstract: A method of method of processing an image of a video sequence including a plurality of images, wherein the video sequence is divided into a sequence of consecutive subsets each including one or more consecutive images of the video sequence is provides, which includes: determining, among the consecutive subsets, a current subset that includes the image, upon determining that the image is a first image of the current subset to be processed, determining an analysis window corresponding to the current subset, wherein the analysis window includes a plurality of consecutive images of the video sequence, and includes at least one image of the current subset, and generating processing results for the image by performing a processing on the images of the analysis window.

Abstract: A video decoding method is disclosed and performed by an electronic device, the method including: obtaining a first resolution used in decoding a current block and a second resolution used in decoding a reference block in a current video frame, the reference block being a reference block used for performing directional prediction on the current block in the current video frame; building a reconstruction block from the reference block; when the first resolution is greater than the second resolution, adjusting the reconstruction block of the reference block to the first resolution to obtain a first reconstruction block; and performing directional prediction on the current block according to the first reconstruction block and the current block.

Abstract: The invention relates to a method for decoding an image based on a base layer (Cbase) and enhancement information (Iam), said method comprising the following steps: decoding said base layer (Cbase) in order to obtain at least one base component (Ydecbase, Udecbase, Vdecbase), oversampling the at least one base component (Ydecbase, Udecbase, Vdecbase) in order to obtain at least one oversampled component (Ysurech, Usurech, Vsurech), decoding the enhancement information (Iam) by means of a part (B) at least of artificial neural network in order to obtain enhancement values (Vam), reconstructing the image based on the at least one oversampled component (Ysurech, Usurech, Vsurech) and the enhancement values (Vam). The invention also relates to associated encoding method, electronic decoding device, electronic encoding device and signal.

Abstract: Methods and systems include receiving, at de-ringing circuitry of a display pipeline of an electronic device, scaled image content based on image data. The de-ringing circuitry also receives a fallback scaler output. The de-ringing circuitry determines whether the image data has a change frequency greater than a threshold. In response to the change frequency being above the threshold, the de-ringing circuitry determines a weight. Based at least in part on the weight, the de-ringing circuitry blends the scaled image content and the fallback scaler output based at least in part on the weight.

Abstract: Embodiments relate to a multi-mode demosaicing circuit able to receive and demosaic image data in a different raw image formats, such as Bayer raw image format and Quad Bayer raw image format. The multi-mode demosaicing circuit comprises different circuitry for demosaicing different image formats that access a shared working memory. In addition, the multi-mode demosaicing circuit shares memory with a post-processing and scaling circuit configured to perform subsequent post-processing and/or scaling of the demosaiced image data, in which the operations of the post-processing and scaling circuit are modified based on the original raw image format of the demosaiced image data to use different amounts of the shared memory, to compensate for additional memory utilized by the multi-mode demosaicing circuit when demosaicing certain types of image data.

Abstract: A method for video processing using Cross-Component Adaptive Loop Filter (CCALF) is provided. The method includes filtering decoded video content using a CCALF, wherein the CCALF is a 24-tap 9×9 filter.

Abstract: The present disclosure provides systems and methods for processing video content using motion compensation interpolation. The methods include: in response to a target picture and a reference picture having different resolutions, applying a band-pass filter to the reference picture, to perform a motion compensated interpolation with reference down-sampling to generate a reference block; and encoding or decoding a block of the target picture using the reference block.

Abstract: Provided are a Reduced Instruction Set Computer-Five (RISC-V)-based artificial intelligence inference method and system. The RISC-V-based artificial intelligence inference method includes the following steps: acquiring an instruction and data of artificial intelligence inference by means of a Direct Memory Access (DMA) interface, and writing the instruction and the data into a memory; acquiring the instruction from the memory and translating the instruction, and loading the data from the memory to a corresponding register on the basis of the instruction; in response to the instruction being a vector instruction, processing, by a convolution control unit, corresponding vector data in a vector processing unit on the basis of the vector instruction; and feeding back the processed vector data to complete inference.

Abstract: Provided are methods and apparatus for creating super-compressed map files. Using free and open-source software (FOSS), the tool create a super-compressed internally tiled Geo Tag Image File Format (TIFF) in a WGS84 datum (WGS84) similar in size to the original LizardTech's MrSID (SID) imagery from the National Geospatial-Intelligence Agency (NGA). Converting NGA data to WGS84 allows mapping systems like NASA Worldwind (WW) to eliminate the step of re-projecting on the fly from non-native projections, thus reducing processing time. The disclosed method includes removing all pure-black pixels by setting them to black+1, changing all near-black border pixels with values less than 15 to 0 (pure black), setting pure black values to “no-data,” compressing the image with a compression scheme, and translating the compressed image to JPEG and a YCbCr color space to achieve greater compression.

Abstract: Provided are an encoder, a decoder and methods for applying and varying a strength of a deblocking or deringing filter for filtering a block of a picture, wherein the deblocking filter is configured to determine, for each of at least eight border portions of a border of the block, a dissimilarity between an unfiltered content of the block and a surrounding picture content around the block along the respective border portion, the eight border portions including four corner border portions, each arranged at a corner of the block, and four edge border portions, each arranged at intermediary portions of the border between the corners of the block. Furthermore, the deblocking filter is configured to parametrize a deblocking filtering of the block using the dissimilarities determined for the at least eight border portions in order to obtain a filtered content of the block.

Abstract: A deblocking method, for deblocking a transform block boundary within a coding block in an image encoding and/or an image decoding is provided, wherein the coding block comprising transform blocks is coded in inter prediction mode and the transform blocks comprises a first transform block and a second transform block; wherein the method comprises: determining, when the boundary between the first transform block and the second transform block is a transform block boundary and at least one of the first transform block and the second transform block has one or more non-zero transform coefficients, a value of a BS parameter for the boundary between the first transform block and the second transform block to be a first value; and performing de-blocking filtering process to the boundary between the first transform block and the second transform block at least based on the value of the boundary strength parameter.

Abstract: When removing a block distortion occurring in a local decoded image, a loop filtering part 11 of an image coding device carries out a filtering process on each of signal components (a luminance signal component and color difference signal components) after setting the intensity of a filter for removing the block distortion for each of the signal components according to a coding mode (an intra coding mode or an inter coding mode) selected by a coding controlling part 1.

Abstract: The present technology relates to a camera, a control method, and a program capable of improving image quality. An image sensor captures an image, and an encoding unit encodes the image. A control unit controls a bit rate to be allocated to encode the image in response to a shake of the camera. The present technology is applicable to, for example, a camera that captures and encodes an image.

Abstract: The disclosure relates to an artificial intelligence (AI) system that uses a machine learning algorithm and an application thereof. A method for controlling an electronic apparatus according to the disclosure includes receiving image data and information associated with a filter set that is applied to an artificial intelligence model for upscaling the image data from an external server; decoding the image data; upscaling the decoded image data using a first artificial intelligence model that is obtained based on the information associated with the filter set; and providing the upscaled image data for output.

Abstract: Systems and methods are provided herein that implement and utilize temporal state machines and other temporal computational/memory circuits. For example, a temporal state machine is provided that comprises a temporal computational unit comprising at least one circuit to perform a time-domain operation, and a temporal memory unit. Both the temporal computational unit and temporal memory unit can operate using solely, or partially, time-encoded wavefronts. The computation unit accesses time-encoded wavefronts from the memory and can output and write time-encoded wavefronts back to the memory.

Abstract: In encoding a picture, comprising a plurality of tiles, into a bitstream, a method and apparatus is provided for signaling the tile attribute values per-tile, using a compact syntax. These embodiments signal per-tile attribute values. The tile attributes may, for example, be in the form of a set of tile syntax elements (one syntax element per tile attribute), or for example in the form of a set of flags to enable or disable the usage of the tile attributes. These embodiments provide freedom for an encoder to assign the tile attribute values per tile, or per any subset of tiles in a picture, and the attribute values are signaled in a compact syntax at least once. A corresponding method and apparatus for decoding a picture is also described.

Abstract: A video picture encoding and decoding method, including obtaining a primary sub-region bitstream corresponding to a target sub-picture of a panoramic picture, where the primary sub-region bitstream includes N secondary sub-region bitstreams, and N is a positive integer, parsing the primary sub-region bitstream to obtain a reconstructed picture, performing cross-sub-region-boundary out-loop filtering on the reconstructed picture when an out-loop filtering identifier instructs to perform cross-sub-region-boundary out-loop filtering on the reconstructed picture, to obtain a filtered reconstructed picture, and adjusting a location of at least one of N sub-regions in the filtered reconstructed picture to obtain a picture having no sub-region boundary.

Abstract: A mechanism is described for facilitating depth and motion estimation in machine learning environments, according to one embodiment. A method of embodiments, as described herein, includes receiving a frame associated with a scene captured by one or more cameras of a computing device; processing the frame using a deep recurrent neural network architecture, wherein processing includes simultaneously predicating values associated with multiple loss functions corresponding to the frame; and estimating depth and motion based the predicted values.