Abstract: A method for encoding a video image using coding parameters, adapted on the basis of motion of the video image and of an output of a machine-learning based model, wherein the machine-learning based model is input with samples of a block of the video image and motion information of the samples, and along with texture, wherein the machine-learning model segments the video image into regions based on strength of the motion determined from the motion information. An object is detected within the video based on the motion and the texture, and spatial-time coding parameters are determined based on the strength of the motion, and whether or not the detected objects moves.

Abstract: The present disclosure relates to pre-processing of video images. In particular, the video images are pre-processed in an object-based manner, i.e., by applying different pre-processing to different objects detected in the image. Moreover, the pre-processing is applied to a group of images. As such, object detection is performed in a plurality of images and the pre-processing for the plurality of images may be adapted to the decoded images and is applied to the decoded images.

Abstract: This disclosure relates to a device for digital signal processing, particularly video image processing. The device obtains image data comprising a plurality of pixels. The image data comprises a plurality of sequentially captured images. The device estimates, for a target image, a set of backward motion vector fields (backward MVFs) based on the target image, and a first set of images captured before the target image. The device further estimates a set of forward MVFs based on the target image and a second set of images captured after the target image. Depending on the estimating for the target image, the device generates an output image based on a merging procedure of the target image and the first set of images and the set of backward MVFs, and/or the second set of images and the set of forward MVFs.

Abstract: An image processing apparatus processes a color filter mosaic, CFM, image of a scene into a final image of the scene. The image processing apparatus includes processing circuitry configured to implement a neural network. The neural network is configured to process the CFM image into an enhanced CFM image. The processing circuitry is further configured to transform the enhanced CFM image into the final image.

Abstract: The present disclosure relates to hybrid video and feature encoding and decoding, with the encoding and decoding of the image feature being performed independently or differentially. The video and feature are encoded and decoded in separate layers, e.g., base layer and enhancement layer. The feature is extracted for a frame of the video, providing a frame-based feature-video association. A feature is extracted from an uncompressed video encoded in an enhancement layer into a feature bitstream. The video is encoded into a video bitstream, with the feature bitstream being embedded into the video bitstream by multiplexing both streams into an output bitstream. The image feature, which may be a differential image feature, is included in a sequence enhancement information SEI message of a frame header information of the video.

Abstract: A method for encoding a video image using coding parameters, adapted on the basis of motion of the video image and of an output of a machine-learning based model, wherein the machine-learning based model is input with samples of a block of the video image and motion information of the samples, and along with texture, wherein the machine-learning model segments the video image into regions based on strength of the motion determined from the motion information. An object is detected within the video based on the motion and the texture, and spatial-time coding parameters are determined based on the strength of the motion, and whether or not the detected objects moves.

Abstract: An improved technique of compressing image data involves separating a prediction error of image data into distinct factors and applying a separate set of context models to each factor. Such factors may take the form of a sign, a bit category, and a relative absolute value of the prediction error. For each factor, the improved technique provides a set of context models and a procedure for selecting a context model from each respective set. The context model for each factor determines a probability distribution of symbols that may represent that factor, which in turn enables compression of the prediction error. Additionally, the symbols that represent certain factors into which the prediction error is separated result from a binary representation whose form—either unary or uniform—depends on the size of the prediction error.

Abstract: An improved technique of compressing image data involves separating a prediction error of image data into distinct factors and applying a separate set of context models to each factor. Such factors may take the form of a sign, a bit category, and a relative absolute value of the prediction error. For each factor, the improved technique provides a set of context models and a procedure for selecting a context model from each respective set. The context model for each factor determines a probability distribution of symbols that may represent that factor, which in turn enables compression of the prediction error. Additionally, the symbols that represent certain factors into which the prediction error is separated result from a binary representation whose form—either unary or uniform—depends on the size of the prediction error.

Abstract: Methods, apparatus, systems and articles of manufacture to perform block-based static region detection for video processing are disclosed. Disclosed example video processing methods include segmenting pixels in a first frame of a video sequence into a first plurality of pixel blocks. Such example methods can also include processing the first plurality of pixel blocks and a second plurality of pixel blocks corresponding to a prior second frame of the video sequence to create, based on a first criterion, a map identifying one or more static pixel blocks in the first plurality of pixel blocks. Such example methods can further include identifying, based on the map, a static region in the first frame of the video sequence.

Abstract: An improved lossless image compression technique involves adaptively selecting between spatial prediction and inter-component prediction techniques depending on which allows better results for any given component of a digital image pixel.

Abstract: Methods, apparatus, systems and articles of manufacture to perform block-based static region detection for video processing are disclosed. Disclosed example video processing methods include segmenting pixels in a first frame of a video sequence into a first plurality of pixel blocks. Such example methods can also include processing the first plurality of pixel blocks and a second plurality of pixel blocks corresponding to a prior second frame of the video sequence to create, based on a first criterion, a map identifying one or more static pixel blocks in the first plurality of pixel blocks. Such example methods can further include identifying, based on the map, a static region in the first frame of the video sequence.

Abstract: A method includes calculating a Fourier transform of an image, extracting a plurality of arrays, from the Fourier transform utilizing, for each of the plurality of arrays, one of a plurality of templates each of said templates corresponding to a texture orientation, calculating a maximum value for each of the plurality of arrays, identifying each of the plurality of arrays having a calculated maximum value greater than a predetermined threshold and determining, for each of the plurality of identified arrays, the texture orientation of the template utilized to extract the identified one of the plurality of arrays.

Abstract: An improved lossless image compression technique involves adaptively selecting between spatial prediction and inter-component prediction techniques depending on which allows better results for any given component of a digital image pixel.

Abstract: A method includes performing a hierarchal motion estimation operation to generate an interpolated frame from a first frame and a second frame, the interpolated frame disposed between the first frame and the second frame, said hierarchal motion estimation including performing two or more process iterations, each iteration including: (a) performing an initial bilateral motion estimation operation on the first frame and the second frame to produce a motion field comprising a plurality of motion vectors, (b) performing a motion field refinement operation for the plurality of motion vectors, (c) performing an additional bilateral motion estimation operation on the first frame and the second frame and (d) repeating steps (b) through (c) until a stop criterion is encountered.

Abstract: A method includes calculating a Fourier transform of an image, extracting a plurality of arrays, from the Fourier transform utilizing, for each of the plurality of arrays, one of a plurality of templates each of said templates corresponding to a texture orientation, calculating a maximum value for each of the plurality of arrays, identifying each of the plurality of arrays having a calculated maximum value greater than a predetermined threshold and determining, for each of the plurality of identified arrays, the texture orientation of the template utilized to extract the identified one of the plurality of arrays.