Abstract: An object of the present disclosure is to restore a quantization error of an image signal only by expanding the number of bits of a reconstructed image compared to the number of bits of an input image without expanding the number of bits in an image signal processing process. An image display apparatus may include a signal inputter configured to receive an input image signal; an image signal processor configured to perform image processing of the input image signal, to identify a type of image processing by comparing the input image signal and the processed image signal, to obtain restoration information of the processed image signal according to the identified image processing type, and to restore an error of the processed image signal by performing remapping of the processed image signal using the restoration information; and an outputter configured to output the image signal in which the error is restored.

Abstract: Provided is an image predicting method including: obtaining a plurality of adjacent samples located adjacent to a current block; determining an adjacent sample as a reference sample to be referred to by a current sample, the adjacent sample being from among the plurality of adjacent samples and being indicated by a direction of an intra mode of the current block; and adjusting a sample value of the reference sample according to a reference distance indicating a distance between the reference sample and the current sample, and determining a prediction value of the current sample based on the adjusted sample value of the reference sample.

Abstract: The present invention relates to an image encoding and decoding technique, and more particularly, to an image encoder and decoder using unidirectional prediction. The image encoder includes a dividing unit to divide a macro block into a plurality of sub-blocks, a unidirectional application determining unit to determine whether an identical prediction mode is applied to each of the plurality of sub-blocks, and a prediction mode determining unit to determine a prediction mode with respect to each of the plurality of sub-blocks based on a determined result of the unidirectional application determining unit.

Abstract: A method and apparatus for video coding using block partition are disclosed. According to the present invention, a partition structure corresponding to recursively partitioning a current block into smaller TU (transform unit) blocks until the partition structure reaches a maximum allowed split depth or until a block size of at least one of smaller TU blocks is a supported core transform size, where the current block is partitioned into final smaller TU blocks according to the partition structure. A transform coding process is applied to the current block according to the partition structure, where the transform coding process is skipped for at least one of the final smaller TU blocks. A flag can be signalled for the current block to indicate whether the current block is allowed to skip the transform coding process for said at least one of the final smaller TU blocks.

Abstract: Disclosed are a method for decoding a video signal and an apparatus therefor. Specifically, a method for decoding an image may include: partitioning a current coding tree block into a plurality of coding blocks so that coding blocks partitioned from the current coding tree block are included in a current picture when the current coding tree block is out of a boundary of the current picture; parsing a first syntax element indicating whether a current coding block is partitioned into a plurality of subblocks when the current coding block satisfies a predetermined condition; and determining a split mode of the current coding block based on the syntax element.

Abstract: A method, computer program, and computer system is provided for encoding video data. Data corresponding to a video frame is received. The video frame data is divided into one or more coding tree units having a height value greater than 128 pixels and a width value greater than 128 pixels. One or more of the coding tree units are further subdivided to a size smaller than 128 pixels by 128 pixels. The video data is encoded based on the divided and subdivided coding tree units.

Abstract: A method for decoding an encoded code stream is provided. The method may include obtaining the encoded code stream. The method may include determining a plurality of code blocks based on the encoded code stream. The method may include determining a plurality of bit-planes for each of the plurality of code blocks, the plurality of bit-planes ranging from a most significant bit-plane to a least significant bit-plane. The method may include determining at least one query-plane for each of the plurality of bit-planes. The method may further include decoding each of the plurality of bit-planes based on the at least one query-plane.

Abstract: A system for using decoder information in video super resolution processing. A compressed video buffering module is used for receiving a compressed video stream and a decoder module is used for decoding the compressed video stream into an uncompressed stream and extracting motion vector information from the uncompressed stream. A video super resolution deep neural network processor module is used for processing the uncompressed stream in conjunction with the motion vector information to produce a video super resolution stream. An output buffer module is used for buffering the video super resolution stream for subsequent output.

Abstract: Systems and methods for performing motion vector prediction for video coding are disclosed. A motion vector predictor is determined based at least in part on motion information associated with a selected motion vector predictor origin and offset values corresponding to a selected sampling point. The sampling point is specified according to a set of direction and distance on a sampling map for the motion vector predictor origin.

Abstract: Circuity for executing operations is provided. The operations obtain pieces of coded data that is included in a bitstream and generated by coding tiles. The pieces of coded data are decoded to generate image data of the tiles. When the pieces of coded data are obtained, tile boundary independence information is further obtained, which indicates whether each of boundaries between the tiles is one of a first boundary and a second boundary. When the pieces of coded data are decoded, image data of a first tile is generated by decoding a first code string included in first coded data with reference to decoding information of an already-decoded tile when the tile boundary independence information indicates the first boundary, and by decoding the first code string without referring to the decoding information of the already-decoded tile when the tile boundary independence information indicates the second boundary.

Abstract: An apparatus and method for successive multi-frame image denoising are herein disclosed. According to one embodiment, an apparatus includes a Wiener filter configured to filter a frame of an image; and a frame delayer configured to feedback the filtered frame to the Wiener filter, wherein the Wiener filter is further configured to filter a subsequent frame of the image based on the filtered frame.

Abstract: Disclosed is a method of encoding a video sequence according to a first set of encoding parameters is presented, including redimensioning the video sequence, generating encoding data of the redimensioned video sequence according to a second set of encoding parameters, determining first encoding data of the video sequence by respective scale transposition of encoded data generated for the redimensioned video sequence, determining, for at least one encoding block of an image of the video sequence, respective pixel residuals from predictive coding data obtained by encoding the redimensioned video sequence applying a block transformation to the pixel residuals determined, and inserting the transformed pixel residuals and the first encoding data into a binary encoding stream of the video sequence.

Abstract: In one embodiment, a method includes obtaining an image comprising a plurality of pixels. The method includes determining, for a particular pixel of the plurality of pixels, a feature value. The method includes selecting, based on the feature value, a set of selected pixels from a set of candidate pixels in an image region surrounding the particular pixel. The method includes denoising the particular pixel based on the set of selected pixels.

Abstract: Transform modes are derived for inter-predicted blocks using side information available within a bitstream. An inter-predicted encoded video block and side information are identified within a bitstream. Based on the side information, a trained transform is determined for inverse transforming transform coefficients of the inter-predicted encoded video block from amongst multiple trained transforms. The transform coefficients of the inter-predicted encoded video block are inverse transformed according to the trained transform to produce a prediction residual. A video block is reconstructed using the prediction residual and the reference frame. The video block is then output within an output video stream for storage or display. To determine the trained transforms, a learning model uses individual side information types and combinations of the individual side information types processed against a training data set.

Abstract: Disclosed herein are systems and methods for detecting when geometry shaders output a constant amount of data and writing the data into an output stream buffer. In one aspect, an exemplary method comprises gathering information about a number of block executions associated with the received data, analyzing the gathered information to determine whether constant or variable amount of data is generated for at least one of: a stream output or a rasterization, and when the constant amount of data is generated for the stream output, writing the generated data directly into a stream output buffer, and when the constant amount of data is generated for the rasterization, writing the generated data into a rasterization buffer either directly or through a use of an intermediate index buffer.

Abstract: Disclosed are various embodiments for staged user enrollment using audio devices. In one embodiment, among others, a system includes a computing device and program instructions. The program instructions can cause the computing device to receive a configuration profile for configuring a client device. The configuration profile includes a device policy associated with an organizational group. The program instructions can further cause the computing device to generate a sound payload based on encoding the configuration profile onto a sound signal. A request is received a request from a voice assistant service for configuring the client device. The request is associated with configuring the client device according to the device policy. The sound payload is transmitted to the voice service for broadcasting from a speaker device. The sound payload is broadcast within an audible distance of the client device.

Abstract: A method for driving a display, a display device, and a source driver. The method includes receiving and storing data obtained by dividing and compressing an image frame, decompressing the data, scanning the decompressed data, storing a result of the scanning, and displaying an image corresponding to the scan result.

Abstract: Methods and apparatuses for coding and decoding mode information and electronic device. The method for coding includes determining a uniform transform block mode adopted by a coding block of an image; determining a binary bit to which the uniform transform block mode corresponds according to a size of the coding block and/or a determined number of uniform transform block modes; and coding the binary bit to which the uniform transform block mode corresponds into a bit stream of the image. Hence, for example, not only uniform transform block mode information may be coded and decoded, but also bit costs of coding may be lowered.

Abstract: A method of encoding a video includes: splitting a picture into a maximum coding unit; for the maximum coding unit, determining coding units having a tree structure including coding units of coded depths and determining encoding modes for the coding units of the coded depths by performing encoding based on coding units according to depths, the coding units according to depths obtained by hierarchically splitting the maximum coding unit as a depth deepens; and outputting information about a maximum coding unit size and, for the maximum coding unit, information indicating an order of split information and skip mode information which is selectively determined for the coding units according to depths, information about the encoding modes for the coding units of the coded depths including the split information and the skip mode information which are arranged according to the order, and encoded video data.

Abstract: The present invention is made to enable switching between lossless coding which prioritizes compatibility with a lossy coding process and lossless coding which prioritizes compression performance. An image coding apparatus of the present invention includes the following configuration. The image coding apparatus which encodes an image on a block-by-block basis includes a first coding unit and a second coding unit. The first coding unit performs irreversible compression coding on a received first block. The second coding unit performs reversible compression coding on a received second block. The second coding unit encodes the second block by using either of a first intra prediction mode for performing intra prediction on a block-by-block basis and a second intra prediction mode for performing intra prediction on a pixel-by-pixel basis.

Abstract: A Moving Picture Experts Group-4 (MP4) file processing method in the embodiments of this application includes storing private media information into a header of media data (MDAT) of an MP4 file during recording of the MP4 file, where the private media information includes a media information parameter of frame data in the MP4 file, and storing index information of the frame data into the MDAT at intervals, where the index information includes time domain information and space domain information of the frame data.

Abstract: An encoder includes processing circuitry and a memory coupled to the processing circuitry. Using the memory, the processing circuitry is configured to: change values of pixels in a first block and a second block to filter a boundary between the first block and the second block. The pixels include type one pixels and type two pixels different from the type one pixels. The first set of filter coefficients applied to the type one pixels in the first block and the second set of filter coefficients applied to the type one pixels in the second block are selected to be asymmetrical with respect to the boundary based on block sizes of the first block and the second block.

Abstract: A moving image encoding device includes a memory, and a processor coupled to the memory and configured to partition a picture edge block into sub-blocks so that none of the sub-blocks include an edge of a picture by partitioning the picture edge block into four or two, the picture edge block being a block including a horizontal or vertical edge of the picture among blocks of the picture, generate a prediction block by referring to another encoded picture or an encoded area of the picture for each of the sub-blocks, calculate a prediction error between a pixel of a given sub-block and a corresponding pixel of the prediction block corresponding to the given sub-block for each of the sub-blocks and encode the prediction error, and add partitioning information indicating whether the picture edge block has been partitioned into four or two, to encoded moving image data.

Abstract: A method of processing video data includes classifying, by processing circuitry, luma samples of a neighboring luma block of a reference block and luma samples of a neighboring luma block of a current block into a plurality of groups and deriving, by the processing circuitry, one or more local illumination compensation parameters for each group of the plurality of groups to generate a plurality of local illumination compensation parameters for the current block. The method further includes deriving, by the processing circuitry, a plurality of linear models between the neighboring luma block of the reference block and the neighboring luma block of the current block using the plurality of local illumination compensation parameters for the current block and generating, by the processing circuitry, a prediction block using the plurality of linear models.

Abstract: Lossless compression of fragmented image data is disclosed. In some embodiments, a stream of information is received, wherein the stream of information comprises a sequence of tuples and wherein each of the tuples comprises data elements corresponding to one of a plurality of input channels. A channel transformer is employed to rearrange the data elements into a plurality of output channels for an output stream wherein the output channels have higher compressibility than the input channels. The compressed output stream is stored.

Abstract: A data encoding method for encoding an array of data values as data sets and escape codes for values not encoded by the data sets, an escape code including a unary coded portion and a non-unary coded portion, the method including: setting a coding parameter defining a minimum number of bits of a non-unary coded portion; adding an offset value of 1 or more to the coding parameter to define a minimum least significant data portion size; generating one or more data sets indicative of positions, relative to the array of data values, of data values of predetermined magnitude ranges, to encode the value of at least one least significant bit of each data value; generating respective complementary most-significant data portions and least-significant data portions; encoding the data sets; encoding the most significant data portions; and encoding the least-significant portions.

Abstract: Various embodiments are generally directed to techniques for embedding a data object into a multidimensional frame, such as for training an autoencoder to generate latent space representations of the data object based on the multidimensional frame, for instance. Additionally, in one or more embodiments latent space representations of data objects may be classified, such as with a machine learning algorithm. Some embodiments are particularly directed to embedding a data object comprising a plurality of object entries into a three-dimensional (3D) frame.

Abstract: A system comprises an encoder configured to compress attribute information for a point cloud and/or a decoder configured to decompress compressed attribute for the point cloud. To compress the attribute information, attribute values are predicted using one of a plurality of prediction strategies, wherein a selected prediction strategy is selected based at least in part on attribute variability of points in a neighborhood of points. A decoder follows a similar prediction process. Also, attribute correction values may be determined to correct predicted attribute values and may be used by a decoder to decompress a point cloud, wherein the decoder applies the same prediction strategy applied at the encoder.

Abstract: An information processing device includes circuitry to generate content based on image data of an original image drawn on a medium. The content is available for use with a terminal device. The circuitry further acquires identification information uniquely identifying the original image. The circuitry further registers the generated content and the acquired identification information, in association with each other. The content and the identification information are registered in association with each other, to an information acquisition destination from which the terminal device is to acquire information based on the identification information.

Abstract: A decoder for decoding a block of a current frame of a video from a bitstream, the decoder comprising a reference sample selection unit configured to select reference samples of a reconstructed part of the current frame, a filter unit configured to filter the reference samples, and a block generation unit configured to generate a prediction of the block based on the filtered reference samples, wherein the filter unit comprises a sharpening filter and/or a de-ringing filter.

Abstract: Systems and methods in accordance with embodiments of the invention are configured to render images using light field image files containing an image synthesized from light field image data and metadata describing the image that includes a depth map. One embodiment of the invention includes a processor and memory containing a rendering application and a light field image file including an encoded image, a set of low resolution images, and metadata describing the encoded image, where the metadata comprises a depth map that specifies depths from the reference viewpoint for pixels in the encoded image. In addition, the rendering application configures the processor to: locate the encoded image within the light field image file; decode the encoded image; locate the metadata within the light field image file; and post process the decoded image by modifying the pixels based on the depths indicated within the depth map and the set of low resolution images to create a rendered image.

Abstract: Techniques for performing learnt image compression and object detection using compressed image data are described. A system may perform image compression using an image compression model that includes an encoder, an entropy model, and a decoder. The encoder, the entropy model, and the decoder may be jointly trained using machine learning based on training data. After training, the encoder and the decoder may be separated to encode image data to generate compressed image data or to decode compressed image data to generate reconstructed image data. In addition, the system may perform object detection using a compressed object detection model that processes compressed image data generated by the image compression model. For example, the compressed object detection model may perform partial decoding using a single layer of the decoder and perform compressed object detection on the partially decoded image data.

Abstract: A method for preventing breach of original data for deep learning is provided. The method includes steps of: a data breach preventing device (a) adding noise onto the acquired original data to generate 1-st noisy data; and (b)(b1) while increasing an integer k from 1 to an integer larger than 0, (i) inputting k-th noisy data into a learning network, to apply learning operations to the k-th noisy data using learned parameters of the learning network, and to output k-th characteristic information, and (ii) launching an adversarial attack on the k-th noisy data via backpropagation using at least one of (ii-1) (k_1)-st losses calculated using the k-th characteristic information and a 1-st ground truth, and (ii-2) (k_2)-nd losses calculated using (1) a k-th task specific output and (2) a 2-nd ground truth, and generating (k+1)-th noisy data, and (b2) as a result, generating n-th noisy data as watermarked data.

Abstract: A method, an electronic device, and a storage medium are provided for processing an image. The method includes: at least one first image frame is acquired based on a first pixel arrangement pattern when receiving a photographing instruction, where a pixel in the first pixel arrangement pattern includes sub-pixels of the same color component distributed in a square array in a photosensitive element; at least one second image frame is acquired based on a second pixel arrangement pattern, where the second pixel arrangement pattern is a standard Bayer arrangement pattern; and the at least one first image frame and the at least one second image frame are fused to obtain the image to be displayed.

Abstract: A method can include identifying, by processing circuitry of a device, a row of rows and/or column of columns to which a first feature and a second feature of an input maps, comparing the identified row and/or column to a row run length encoding (RLE) in a memory of the device that indicates, for each row, whether one or more cells in the row include an input mapped thereto or a column RLE in a memory of the device that indicates, for each column, whether one or more cells in the column include an input mapped thereto, respectively, and determining the input data is anomalous in response to determining either the row RLE indicates that no inputs are mapped to the row to which the input maps, or the column RLE indicates that no inputs are mapped to the column to which the input maps.

Abstract: A medical observation system including a medical imaging device that captures a plurality of images of a living body while changing a focus position, and circuitry that generates a composite image by compositing the plurality of images captured by the medical imaging device, and switches output between the generated composite image and one of the plurality of images based on a result of analysis performed on at least one of the plurality of images.

Abstract: Motion adaptive shading increases rendering performance for real-time animation in graphics systems while maintaining dynamic image quality. Each frame of an animation is statically displayed within a refresh interval, while a viewer's eyes move continuously relative to the image when actively tracking a moving object being displayed. As a result, a statically displayed frame is essentially smeared across the viewer's continuously moving retina over the lifetime of the frame, causing a perception of blur referred to as an eye-tracking motion blur effect. A region of an image depicting a moving object may be rendered at a lower shading rate because eye-tracking motion blur will substantially mask any blur introduced by reducing the shading rate. Reducing an average shading rate for rendering frames reduces computational effort per frame and may advantageously allow a rendering system to operate at a higher frame rate to provide a smoother, clearer visual experience.

Abstract: There is provided a primary beam scanning apparatus capable of producing data having a bit depth higher than the resolution of an analog-to-digital converter. The primary beam scanning apparatus is capable of controlling a scan rate of a primary beam for scanning a specimen. The scanning apparatus includes a detector for detecting signals generated in response to irradiation of the specimen with the primary beam and providing an analog output signal, an analog-to-digital converter for sampling the analog signal and converting it into a digital signal, and an arithmetic section for averaging the digital signal.

Abstract: The present invention relates to an image encoding and decoding technique, and more particularly, to an image encoder and decoder using unidirectional prediction. The image encoder includes a dividing unit to divide a macro block into a plurality of sub-blocks, a unidirectional application determining unit to determine whether an identical prediction mode is applied to each of the plurality of sub-blocks, and a prediction mode determining unit to determine a prediction mode with respect to each of the plurality of sub-blocks based on a determined result of the unidirectional application determining unit.

Abstract: Described herein is a system for executing a computing module. Described herein is a system for executing a computing module. The system may determine whether a function of a computing module is suitable to be executed using multi-coring. The system identifies one or more available computing cores and executes the function on the one or more available computing cores. The one or more available computing cores can be dedicated to execute the function until the execution of the function is complete. The one or more available computing cores execute the tasks of the function asynchronously. The system receives output data from the function asynchronously in a list data structure. The system can maintain a desired order of the output data in the list data structure.

Abstract: Methods and apparatuses of decoding a video stream encoded using video point cloud coding include obtaining a geometry-reconstructed point cloud; dividing the geometry-reconstructed point cloud into a plurality of cells; obtaining a first reference point including a centroid of a first plurality of points; generating a second plurality of points by applying a first filter to the first plurality of points based on the first reference point; obtaining a second reference point including a centroid of the second plurality of points; generating a third plurality of points by applying a second filter to the second plurality of points based on the second reference point, wherein a strength of the first filter is higher than a strength of the second filter; obtaining a smoothed geometry-reconstructed point cloud based on the third plurality of points; and reconstructing a dynamic point cloud using the smoothed geometry-reconstructed point cloud.

Abstract: A method of signaling additional chroma QP offset values that are specific to quantization groups is provided, in which each quantization group explicitly specifies its own set of chroma QP offset values. Alternatively, a table of possible sets of chroma QP offset values is specified in the header area of the picture, and each quantization group uses an index to select an entry from the table for determining its own set of chroma QP offset values. The quantization group specific chroma QP offset values are then used to determine the chroma QP values for blocks within the quantization group in addition to chroma QP offset values already specified for higher levels of the video coding hierarchy.

Abstract: In one example, a method comprises: enabling a photodiode to, in response to incident light, accumulate residual charge, and to transfer overflow charge to a first charge storage device and a second charge storage device when the photodiode saturates; disconnecting the second charge storage device from the first charge storage device; enabling the photodiode to transfer the residual charge to the first charge storage device to cause the charge sensing unit to output a first voltage; quantizing the first voltage to generate a first digital value to measure the residual charge; connecting the second charge storage device with the first charge storage device to cause the charge sensing unit to output a second voltage; quantizing the second voltage to generate a second digital value to measure the overflow charge; and generating a digital representation of the incident light intensity based on the first digital value and the second digital value.

Abstract: Examples of the present disclosure relate to methods for processing image data. In one such example, data elements are received defining a portion of a line of pixels of an image, the image comprising one or more lines of pixels definable by one or more respective sets of data elements. In some cases, a transform operation is performed on the data elements to obtain a plurality of binary transform coefficients, wherein the transform operation is performed independently of data elements defining any other line of pixels. The plurality of transform coefficients is encoded as a sequence of tiered bit-layers, each bit-layer in the sequence of bit-layers comprising a set of bits corresponding to a given bit position in each of the plurality of transform coefficients. The encoded plurality of transform coefficients is output.

Abstract: Embedded Codec (EBC) circuitry for image block coding based on pixel-domain pre-processing operations on image block is provided. The EBC circuitry includes memory that stores a first image block and encoder circuitry that computes a first sum of absolute differences (SAD) from a first prediction block of row-wise residual values and a second SAD from a second prediction block of column-wise residual values in pixel-domain. The encoder circuitry selects a residual prediction type from a set of residual prediction types as an optimal residual prediction type and a set of quantization parameters as optimal quantization parameters for each of a first encoding mode and a second encoding mode. The encoder circuitry generates a set of bit-streams of encoded first image block in the first encoding mode and the second encoding mode, respectively, based on the selected residual prediction type and the selected set of quantization parameters.

Abstract: Some embodiments provide a novel compressive-sensing image capture device and a method of using data captured by the compressive-sensing image capture device. The novel compressive-sensing image capture device includes an array of sensors for detecting electromagnetic radiation. Each sensor in the sensor array has an associated mask that blocks electromagnetic radiation from portions of the sensor. In some embodiments, an array of passive masks is used to block a particular set of areas of each sensor in the sensor array. In some embodiments, the image capture device also includes an array of lenses corresponding to the sensors of the sensor array such that each sensor receives light that passes through a different lens. Some embodiments of the invention provide a dynamic mask array. In some embodiments, a novel machine trained network is provided that processes image capture data captured by the compressive-sensing image capture device to predict solutions to problems.

Abstract: The present invention relates to specification of a tile capable of being independently processed to process a certain area at high speed in encoding and decoding of tiles resulting from division of an image in hierarchical coding of the image. An image encoding apparatus that performs the hierarchical coding of an input image with multiple layers includes an acquiring unit and an encoding unit. The acquiring unit acquires a first image generated from the input image and a second image having resolution different from that of the first image. In the encoding of a first area in the first image acquired by the acquiring unit, the encoding unit performs the encoding using a second area existing at the relatively same position as that of the first area in the first image in the second image as a reference image.

Abstract: An image and video compression method includes defining one or more encoding quality patterns, the one or more encoding quality patterns each have pre-determined areas of quality adjustment, the pre-determined areas of quality adjustment including one or more pre-defined regions of lower quality adjustment and one or more pre-defined regions of higher quality adjustment; receiving a frame associated with content to be encoded; selecting one of the one or more encoding quality patterns; processing the frame via an encoder, the processing using the selected one of the one or more encoded quality patterns; and producing a final output of an encoded bit.

Abstract: Deblocking filtering is provided in which an 8×8 filtering block covering eight sample vertical and horizontal boundary segments is divided into filtering sub-blocks that can be independently processed. To process the vertical boundary segment, the filtering block is divided into top and bottom 8×4 filtering sub-blocks, each covering a respective top and bottom half of the vertical boundary segment. To process the horizontal boundary segment, the filtering block is divided into left and right 4×8 filtering sub-blocks, each covering a respective left and right half of the horizontal boundary segment. The computation of the deviation d for a boundary segment in a filtering sub-block is performed using only samples from rows or columns in the filtering sub-block. Consequently, the filter on/off decisions and the weak/strong filtering decisions of the deblocking filtering are performed using samples contained within individual filtering blocks, thus allowing full parallel processing of the filtering blocks.

Abstract: A set of software applications configured to perform interframe and/or intraframe encoding operations based on data communicated between a graphics application and a graphics processor. The graphics application transmits a 3D model to the graphics processor to be rendered into a 2D frame of video data. The graphics application also transmits graphics commands to the graphics processor indicating specific transformations to be applied to the 3D model as well as textures that should be mapped onto portions of the 3D model. Based on these transformations, an interframe module can determine blocks of pixels that repeat across sequential frames. Based on the mapped textures, an intraframe module can determine blocks of pixels that repeat within an individual frame. A codec encodes the frames of video data into compressed form based on blocks of pixels that repeat across frames or within frames.