Methods, systems, and computer readable media for compressing video images are disclosed. According to one exemplary method, the method includes classifying image pixels in each video image of a series of video images as either foreground or background. The method also includes replacing each pixel classified as background with a time-averaged value of pixel intensity for that pixel. The method further includes compressing the video images using a compression algorithm.

A model-based compression codec applies higher-level modeling to produce better predictions than can be found through conventional block-based motion estimation and compensation. Computer-vision-based feature and object detection algorithms identify regions of interest throughout the video datacube. The detected features and objects are modeled with a compact set of parameters, and similar feature/object instances are associated across frames. Associated features/objects are formed into tracks and related to specific blocks of video data to be encoded. The tracking information is used to produce model-based predictions for those blocks of data, enabling more efficient navigation of the prediction search space than is typically achievable through conventional motion estimation methods. A hybrid framework enables modeling of data at multiple fidelities and selects the appropriate level of modeling for each portion of video data. A compliant-stream version of the model-based compression codec uses the modeling information indirectly to improve compression while producing bitstreams that can be interpreted by standard decoders.

Computer processor hardware receives settings information for a first image. The first image includes a set of multiple display elements. The computer processor hardware receives motion compensation information for a given display element in a second image to be created based at least in part on the first image. The motion compensation information indicates a coordinate location within a particular display element in the first image to which the given display element pertains. The computer processor hardware utilizes the coordinate location as a basis from which to select a grouping of multiple display elements in the first image. The computer processor hardware then generates a setting for the given display element in the second image based on settings of the multiple display elements in the grouping.

Computer processor hardware receives settings information for a first image. The first image includes a set of multiple display elements. The computer processor hardware receives motion compensation information for a given display element in a second image to be created based at least in part on the first image. The motion compensation information indicates a coordinate location within a particular display element in the first image to which the given display element pertains. The computer processor hardware utilizes the coordinate location as a basis from which to select a grouping of multiple display elements in the first image. The computer processor hardware then generates a setting for the given display element in the second image based on settings of the multiple display elements in the grouping.

Intra prediction is used in state-of-the-art video coding standards such as AVC. The intra prediction modes are coded into the bitstream. Luma and chroma components could potentially have different prediction modes. For chroma components, there are 5 different modes defined in AVC: vertical, horizontal, DC, diagonal down right, and “same as luma”. Statistics show that the “same as luma” mode is frequent used, but in AVC, this mode is encoded using more bits than other modes during entropy coding, therefore the coding efficiency is decreased. Accordingly, a modified binarization/codeword assignment for chroma intra mode signaling is able to be utilized for high efficiency video coding (HEVC), the next generation video coding standard.

Intra prediction is used in state-of-the-art video coding standards such as AVC. The intra prediction modes are coded into the bitstream. Luma and chroma components could potentially have different prediction modes. For chroma components, there are 5 different modes defined in AVC: vertical, horizontal, DC, diagonal down right, and “same as luma”. Statistics show that the “same as luma” mode is frequent used, but in AVC, this mode is encoded using more bits than other modes during entropy coding, therefore the coding efficiency is decreased. Accordingly, a modified binarization/codeword assignment for chroma intra mode signaling is able to be utilized for high efficiency video coding (HEVC), the next generation video coding standard.

Systems and methods for reducing, with minimal loss, optical sensor data to be conveyed to another system for processing. An eye tracking device, such as a head-mounted display (HMD), includes a sensor and circuitry. The sensor generates image data of an eye. The circuitry receives the image data, and assigns pixels of the image data to a feature region of the eye by comparing pixel values of the pixels to a threshold value. A feature region refers to an eye region of interest for eye tracking, such as a pupil or glint. The circuitry generates encoded image data by apply an encoding algorithm, such as a run-length encoding algorithm or contour encoding algorithm, to the image data for the pixels of the feature region. The circuitry transmits the encoded image data, having a smaller data size than the image data received from the sensor, for gaze contingent content rendering.

A video compression framework based on parametric object and background compression is proposed. At the encoder, an embodiment detects objects and segments frames into regions corresponding to the foreground object and the background. The object and the background are individually encoded using separate parametric coding techniques. While the object is encoded using the projection of coefficients to the orthonormal basis of the learnt subspace (used for appearance based object tracking), the background is characterized using an auto-regressive (AR) process model. An advantage of the proposed schemes is that the decoder structure allows for simultaneous reconstruction of object and background, thus making it amenable to the new multi-thread/multi-processor architectures.

A video compression framework based on parametric object and background compression is proposed. At the encoder, an embodiment detects objects and segments frames into regions corresponding to the foreground object and the background. The object and the background are individually encoded using separate parametric coding techniques. While the object is encoded using the projection of coefficients to the orthonormal basis of the learnt subspace (used for appearance based object tracking), the background is characterized using an auto-regressive (AR) process model. An advantage of the proposed schemes is that the decoder structure allows for simultaneous reconstruction of object and background, thus making it amenable to the new multi-thread/multi-processor architectures.

The present disclosure relates to a motion compensation method and module, a chip, an electronic device, and a storage medium, to improve the problem of haloes easily appearing on the edges of moving objects.