Abstract: A computer-implemented method for facilitating encoding of video data. The method includes performing an operation to determine prediction residuals associated with a unit of the video data, and, processing, using a neural network arrangement, the prediction residuals associated with the unit of the video data to determine model parameters associated with a rate-distortion model for the unit of the video data. The model parameters are arranged to facilitate encoding of at least the unit of the video data. The method can be applied to multiple ones of such unit of the video data.

Abstract: There is provided a computer-implemented method for learned video compression, which includes processing a current frame (xt) and previously decoded frame ({circumflex over (x)}t-1) of a video data using a motion estimation model to estimate a motion vector (vt) for every pixel, compressing the motion vector (vt) and reconstructing the motion vector (vt) to a reconstructed motion vector ({circumflex over (v)}t), applying an enhanced context mining (ECM) model to obtain enhanced context ({umlaut over (C)}E) from the reconstructed motion vector ({circumflex over (v)}t) and previously decoded frame feature (x?t-1), compressing the current frame (xt) with the assistance of the enhanced context ({umlaut over (C)}E) to obtain a reconstructed frame ({circumflex over (x)}?t), and providing the reconstructed frame ({circumflex over (x)}?t) to a post-enhancement backend network to obtain a high-resolution frame ({circumflex over (x)}t).

Abstract: An AZB detection method for video coding, which includes the steps of detecting if a residual signal includes a spatial domain GAZB; detecting if the residual signal includes a frequency domain GAZB if no spatial domain GAZB is detected in the previous step; detecting if the residual signal includes a PAZB if no frequency domain GAZB is detected in the previous step; and determining that the residual signal is a non-AZB signal if no PAZB is detected in the previous step. The proposed method achieves promising time savings for test sequences of different resolutions, with negligible rate-distortion performance loss.

Abstract: A method for learning-based point cloud geometry compression includes: given a source point cloud, regressing an aligned mesh that is driven by a set of parameters from a deformable template mesh, quantizing the set of parameters into a parameter bitstream, generating an aligned point cloud from the quantized parameters by mesh manipulation and mesh-to-point-cloud conversion, extracting features from both the source point cloud and the aligned point cloud based on sparse tensors including coordinates and features, the coordinates being encoded into a coordinate bitstream, warping the features of the aligned point cloud onto the coordinates of the source point cloud, obtaining residual features through feature subtraction, processing the residual features using an entropy model into a residual feature bitstream, and obtaining a reconstructed point cloud by processing the parameter bitstream, the coordinate bitstream and the residual feature bitstream.

Abstract: A framework that comprises a reinforcement-learning-based neural-network for compressing, and for transmitting the compressed genomes over a data network in repeated steps each of a plurality of species. The framework also takes data on inefficient transmission of compressed genome in the preceding step, and feeds this data forward to modify the selection of the compression parameter in the present step. The invention provides the possibility that the genome of any species may be compressed optimally and transmitted in optimal efficiency. That is, big genome sequence is neither over compressed, which takes a lot of processing time leading to delays, nor under compressed which will require more time to transmit.

Abstract: A computer-implemented method for facilitating encoding of video data. The method includes performing an operation to determine prediction residuals associated with a unit of the video data, and, processing, using a neural network arrangement, the prediction residuals associated with the unit of the video data to determine model parameters associated with a rate-distortion model for the unit of the video data. The model parameters are arranged to facilitate encoding of at least the unit of the video data. The method can be applied to multiple ones of such unit of the video data.

Abstract: A method for learning-based point cloud geometry compression includes: given a source point cloud, regressing an aligned mesh that is driven by a set of parameters from a deformable template mesh, quantizing the set of parameters into a parameter bitstream, generating an aligned point cloud from the quantized parameters by mesh manipulation and mesh-to-point-cloud conversion, extracting features from both the source point cloud and the aligned point cloud based on sparse tensors including coordinates and features, the coordinates being encoded into a coordinate bitstream, warping the features of the aligned point cloud onto the coordinates of the source point cloud, obtaining residual features through feature subtraction, processing the residual features using an entropy model into a residual feature bitstream, and obtaining a reconstructed point cloud by processing the parameter bitstream, the coordinate bitstream and the residual feature bitstream.

Abstract: A method for compressing three-dimensional (3D) medical image. The method includes obtaining image data of a 3D medical image, performing a data conversion operation to convert the image data of the 3D medical image into video data of a sequence of frames each corresponding to a respective 2D image, and performing a video encoding operation to encode the video data of the sequence of frames to obtain encoded content data. The encoded content data can be used for reconstructing the 3D medical image.

Abstract: A method for compressing a 3D medical image includes the steps of receiving a 3D medical image, partitioning the 3D medical image into a plurality of first slices, encoding the plurality of the first slices by a lossy codec into first bitstreams, decoding the first bitstreams by the lossy codec to obtain a plurality of second slices, computing a plurality of residues by comparing the plurality of the first slices and the plurality of the second slices, encoding the plurality of the residues by a lossless codec to obtain a plurality of encoded residues, and outputting the first bitstreams and the plurality of the encoded residues as compressed image data. Each residue corresponds to one of the first slices and its corresponding second slice. Experimental results on prevailing 3D medical image datasets demonstrate that the proposed method achieves promising compression performance and outperforms state-of-the-art methods.

Abstract: There is provided a computer-implemented method for learned video compression, which includes processing a current frame (xt) and previously decoded frame ({circumflex over (x)}t?1) of a video data using a motion estimation model to estimate a motion vector (vt) for every pixel, compressing the motion vector (vt) and reconstructing the motion vector (vt) to a reconstructed motion vector ({circumflex over (v)}t), applying an enhanced context mining (ECM) model to obtain enhanced context ({umlaut over (C)}E) from the reconstructed motion vector ({circumflex over (v)}t) and previously decoded frame feature (x?t?1), compressing the current frame (xt) with the assistance of the enhanced context ({umlaut over (C)}E) to obtain a reconstructed frame ({circumflex over (x)}t?), and providing the reconstructed frame ({circumflex over (x)}t?) to a post-enhancement backend network to obtain a high-resolution frame ({circumflex over (x)}t).

Abstract: There is provided a computer-implemented method for processing a video. The computer-implemented method includes: (a) determining a target frame-level quality required for a frame of the video to be encoded, the determining of the target frame-level quality is based on, at least, a rate-quantization (R-Q) model that relates bit-rate and quantization step size and a quality-quantization model that relates quality measure and the quantization step size; and (b) determining one or more coding parameters for encoding the frame based on the determined target frame-level quality.

Abstract: A system and a method for processing an image. The system comprises an image gateway arranged to receive an input image showing a scene composed by a combination of a plurality of image portions of the input image, wherein one or more of the plurality of image portions is associated with an exposure level deviated from an optimal exposure level; and an enhancement engine arranged to process the input image by applying an exposure/image relationship to the input image, wherein the exposure/image relationship is arranged to adjust the exposure level of each of the plurality of image portions towards the optimal exposure level; and to generate an enhanced image showing a visual representation of the scene composed by a combination of the plurality of image portions of the input image with an adjusted exposure level.

Abstract: A method for adaptive reconstruction of a compressively sensed data. The method contains the steps of receiving sensed data; conducting an initial reconstruction to the sensed data to obtain a plurality of first reconstruction patches; by a reconstruction module, conducting a progressive reconstruction to the sensed data to obtain a plurality of second reconstruction patches; summing the plurality of second reconstruction patches with the a plurality of first reconstruction patches to obtain final patches; and merging the final patches to obtain a reconstructed data. The progressive reconstruction further contains concatenating transformer features and convolution features to obtain the second reconstruction patches. The invention provides a hybrid network for adaptive sampling and reconstruction of CS, which integrates the advantages of leveraging both detailed spatial information from CNN and the global context provided by transformer for enhanced representation learning.

Abstract: A computer-implemented method for facilitating machine-learning based media (e.g., video) compression. The method includes receiving a motion data set associated with motion-related difference between a first image and a second image, and processing the motion data set using a neural network to determine a plurality of motion data subsets. The method also includes processing the plurality of motion data subsets using one or more features associated with the first image to obtain a plurality of motion-warped feature data sets each associated with a respective motion data subset; and processing the plurality of motion-warped feature data sets to facilitate generation of context data for facilitating conditional coding based compression of the second image.

Abstract: A method for processing a screen content video. The screen content video includes a plurality of frames each including a plurality of coding tree units and a plurality of coding units in each of the coding tree units. The method includes performing a coding-tree-unit-based analysis operation on the screen content video to determine content information associated with the screen content video, and performing a rate control operation on the screen content video based on the determined content information to encoding of the screen content video. The content information includes content complexity information associated with the screen content video and temporal importance information associated with the screen content video.

Abstract: A system and a method for processing an image. The system comprises an image gateway arranged to receive an input image showing a scene composed by a combination of a plurality of image portions of the input image, wherein one or more of the plurality of image portions is associated with an exposure level deviated from an optimal exposure level; and an enhancement engine arranged to process the input image by applying an exposure/image relationship to the input image, wherein the exposure/image relationship is arranged to adjust the exposure level of each of the plurality of image portions towards the optimal exposure level; and to generate an enhanced image showing a visual representation of the scene composed by a combination of the plurality of image portions of the input image with an adjusted exposure level.

Abstract: A system and a method for processing an image. The system comprises an image gateway arranged to receive an input image showing a scene composed by a combination of a plurality of image portions of the input image, wherein one or more of the plurality of image portions is associated with an exposure level deviated from an optimal exposure level; and an enhancement engine arranged to process the input image by applying an exposure/image relationship to the input image, wherein the exposure/image relationship is arranged to adjust the exposure level of each of the plurality of image portions towards the optimal exposure level; and to generate an enhanced image showing a visual representation of the scene composed by a combination of the plurality of image portions of the input image with an adjusted exposure level.

Abstract: A system and a method for processing an image. The system comprises an image gateway arranged to receive an input image showing a scene composed by a combination of a plurality of image portions of the input image, wherein one or more of the plurality of image portions is associated with an exposure level deviated from an optimal exposure level; and an enhancement engine arranged to process the input image by applying an exposure/image relationship to the input image, wherein the exposure/image relationship is arranged to adjust the exposure level of each of the plurality of image portions towards the optimal exposure level; and to generate an enhanced image showing a visual representation of the scene composed by a combination of the plurality of image portions of the input image with an adjusted exposure level.

Abstract: A method for processing a stream of images including the steps of obtaining coding information from the stream of images to determine one or more bitrate/distortion models representative of the bitrate/distortion relationship of the stream of images, determining a set of coding parameters arranged for use to encode a stream of images with the one or more bitrate/distortion models, reformulating the bitrate/distortion relationship into a decoupled relationship arranged to be applied to a subset of the stream of images, and using the decoupled relationship and the set of coding parameters to generate an adaptive quantization parameter for encoding the stream of images with the bitrate/distortion relationship.

Abstract: A method for processing a stream of images including the steps of obtaining coding information from the stream of images to determine one or more bitrate/distortion models representative of the bitrate/distortion relationship of the stream of images, determining a set of coding parameters arranged for use to encode a stream of images with the one or more bitrate/distortion models, reformulating the bitrate/distortion relationship into a decoupled relationship arranged to be applied to a subset of the stream of images, and using the decoupled relationship and the set of coding parameters to generate an adaptive quantization parameter for encoding the stream of images with the bitrate/distortion relationship.