An apparatus and method for geometrically correcting a distorted input frame and generating an undistorted output frame. The apparatus includes an external memory block that stores the input frame, a counter block to compute output coordinates of the output frame for a region based on a block size of the region, a back mapping block to generate input coordinates corresponding to each of the output coordinates, a bounding module to compute input blocks corresponding to each of the input coordinates, a buffer module to fetch data corresponding to each of the input blocks, an interpolation module to interpolate data from the buffer module and a display module that receives the interpolated data for each of the regions and stitch an output image. The method includes determining the size of the output block based on a magnification data.

Embodiments for volumetric video encoding and decoding relating to one or more three-dimensional objects are disclosed. In encoding, after mapping from 3D space to 2D plane (802) a point in the 2D plane is examined (805) to determine which points of the 3D object are mapped to the same point to obtain a set of candidate points. Candidate points belonging to a same surface can be used to determine a center of mass for the surface (807). A depth value of the centre of mass is mapped to a 2D projection depth plane (808). A colour value for the centre of mass is interpolated from colour values of points of the set of surface points which are nearest neighbours of the center of mass (810), and used as the colour of the surface in the texture plane (812). Corresponding embodiments for decoding are provided.

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.

A method is provided for generating a personalized Head Related Transfer Function (HRTF). The method can include capturing an image of an ear using a portable device, auto-scaling the captured image to determine physical geometries of the ear and obtaining a personalized HRTF based on the determined physical geometries of the ear. In addition, a system and a method in association with the system are also provided for customizing audio experience. Customization of audio experience can be based on derivation of at least one customized audio response characteristic which can be applied to an audio device used by a person. Finally, methods and systems are provided for rendering audio over headphones with head tracking enabled by, for example, exploiting efficiencies in creating databases and filters for use in filtering 3D audio sources for more realistic audio rendering and also allowing greater head movement to enhance the spatial audio perception.

A method and system for image segmentation systems and related methods of automatically segmenting cardiac MRI images using deep learning methods. One example method includes inputting MRI volume data from a MRI scanner, segmenting the MRI volume data with a whole volume segmentation analysis module, assembling the segmented MRI volume data into a 3D volume assembly with a 3D volume assembly module, determining the 3D volume assembly for anatomic plausibility with an anatomic plausibility analysis module, and outputting a final segmented 3D volume assembly.

An image processing circuit for correcting a distorted image includes an internal memory and a correction circuit. The internal memory of the image processing circuit is configured to store a radial look-up table (LUT), a set of tangential LUTs, and co-ordinates of a correction center of the distorted image. The radial LUT and the set of tangential LUTs include first and second sets of parameters to correct radial and tangential distortion of the distorted image, respectively. The correction circuit is configured to reconstruct portions of the correction LUT on-the-fly based on the radial LUT, the set of tangential LUTs, and the co-ordinates of the correction center, and correct portions of the distorted image based on the reconstructed portions of correction LUT to generate the portions of the corrected image.

A system and a method for monitoring a brain CT scan image using ASPECTS score. The method includes receiving the brain CT scan image of a patient. Further, a basal ganglia region and a corona radiata level are identified in a plurality of slices in the brain CT scan image. Furthermore, a plurality of anatomical regions, a plurality of infarcts and a plurality of black regions are segmented using deep learning. Subsequently, an overlapping region across the plurality of slices is determined based on the plurality of anatomical regions, the plurality of infarcts, and the plurality of black regions. The overlapping region and a predefined threshold are used to compute an ASPECTS score. The ASPECTS score is further used to recommend a course of action to the patient.

The disclosure describes one or more embodiments of systems, methods, and non-transitory computer-readable media that utilize a sharpness map that includes information on how to filter a displacement map on a per-texel basis to preserve sharp features while sampling a displacement map. For instance, the disclosed systems utilize a sharpness map that encodes combinable patterns to represent discontinuities of features within a displacement map. In some embodiments, the disclosed systems generate a sharpness map having texels encoded with discontinuity configurations that are referenced to control filtering (e.g., via interpolation) of a displacement map such that sharp features within the displacement map are not lost (due to smoothing during interpolation). For example, the disclosed systems filter feature values of a displacement map using discontinuities identified within a sharpness map to interpolate when the feature value(s) and a sampling point are identified as being on the same side of a discontinuity.

A method includes receiving, by a computing device, training data comprising a plurality of pairs of images, wherein each pair comprises an image and at least one corresponding target version of the image. The method also includes training a neural network based on the training data to predict an enhanced version of an input image, wherein the training of the neural network comprises applying a forward Gaussian diffusion process that adds Gaussian noise to the at least one corresponding target version of each of the plurality of pairs of images to enable iterative denoising of the input image, wherein the iterative denoising is based on a reverse Markov chain associated with the forward Gaussian diffusion process. The method additionally includes outputting the trained neural network.

This disclosure includes technologies for image processing, particularly for image generation and editing in a configurable semantic direction. A generative adversarial network is trained with an auxiliary network with an auxiliary task that is designed to disentangle the latent space of the generative adversarial network. Resultantly, a new type of GAN is created to improve image generation or editing in both conditional and unconditional settings.