Abstract: Described herein is a graphics processor comprising a system interconnect and a graphics processor cluster coupled with the system interconnect. The graphics processor cluster includes circuitry configurable to generate per-frame neural representations of a multi-view video via incremental training and transferal of weights.

Abstract: Systems, apparatus, articles of manufacture, and methods are disclosed to improve separation mask estimation. An example apparatus includes interface circuitry, instructions, and programmable circuitry to at least one of instantiate or execute the instructions to deactivate a motion network and activate an attribute network in response to a frame input of a stream to a neural network. The example apparatus also executes the instructions to train the attribute network based on the frame input, activate the motion network and deactivate the attribute network in response to a subsequent frame input of the stream to the neural network, train the motion network based on the subsequent frame, and determine pixels of the video stream that are moving.

Abstract: Apparatus and method for a hierarchical beam tracer.

Abstract: Techniques related to generating holographic images for a holographic heads up display are discussed. Such techniques include application of a machine learning model to the target image to generate data that is used to enable the determination of a phase pattern via an iterative propagation feedback model. The iterative propagation feedback model is used to generate a feedback strength value, which is then used to generate a phase diffraction pattern for presentation at a holographic plane of the heads up display.

Abstract: Techniques related to generating holographic images are discussed. Such techniques include application of a hybrid system including a pre-trained deep neural network and a subsequent iterative process using a suitable propagation model to generate diffraction pattern image data for a target holographic image such that the diffraction pattern image data is to generate a holographic image when implemented via a holographic display.

Abstract: Techniques related to generating holographic images are discussed. Such techniques include application of a machine learning model to the target image to generate data that is used to enable the determination of a phase pattern via an iterative propagation feedback model. The iterative propagation feedback model is used to generate a feedback strength value, which is then used to generate a phase diffraction pattern for presentation at a holographic plane.

Abstract: A method and system of holographic image processing includes phase error compensation.

Abstract: Techniques related to generating holographic images are discussed. Such techniques include application of a machine learning model to the target image to generate data that is used to enable the determination of a phase pattern via a wave propagation model. The wave propagation model is used to generate holographic data, which is then adjusted according to one or more constraints associated with the holographic display that will be used to generate a holographic image based on the adjusted holographic data.

Abstract: Techniques related to generating holographic images are discussed. Such techniques include application of a hybrid system including a pre-trained deep neural network and a subsequent iterative process using a suitable propagation model to generate diffraction pattern image data for a target holographic image such that the diffraction pattern image data is to generate a holographic image when implemented via a holographic display.

Abstract: Apparatus and method for a hierarchical beam tracer.

Abstract: Techniques related to generating holographic images are discussed. Such techniques include application of a hybrid system including a pre-trained deep neural network and a subsequent iterative process using a sui table propagation model to generate diffraction pattern image data for a target holographic image such that the diffraction pattern image data is to generate a holographic image when implemented via a holographic display.

Abstract: Techniques related to generating holographic images are discussed. Such techniques include application of a machine learning model to the target image to generate data that is used to enable the determination of a phase pattern via an iterative propagation feedback model. The iterative propagation feedback model is used to generate a feedback strength value, which is then used to generate a phase diffraction pattern for presentation at a holographic plane.

Abstract: Techniques related to generating holographic images are discussed. Such techniques include application of a pre-trained deep neural network to a target holographic image to generate a feedback strength value for error feedback in an iterative propagation feedback model and generating a diffraction pattern image corresponding to the target holographic image by applying the iterative propagation feedback model based on the target holographic image and using the feedback strength value.

Abstract: Techniques related to generating holographic images are discussed. Such techniques include application of a machine learning model to the target image to generate data that is used to enable the determination of a phase pattern via a wave propagation model. The wave propagation model is used to generate holographic data, which is then adjusted according to one or more constraints associated with the holographic display that will be used to generate a holographic image based on the adjusted holographic data.

Abstract: Apparatus and method for a hierarchical beam tracer.

Abstract: Methods and apparatus to calibrate spatial light modulators are disclosed. Examples include processor circuitry to execute and/or instantiate instructions to provide a greyscale image to a spatial light modulator (SLM) to define voltages to be applied to individual pixels of the SLM. The voltages associated with pixel values in the greyscale image. The pixel values arranged in a double-slit grating pattern. The SLM to produce an interference pattern based on the double-slit grating pattern. The processor circuitry is to determine a phase difference between first and second gratings of the double-slit grating pattern based on the interference pattern. The processor circuitry is to generate a phase curvature based on the phase difference.

Abstract: Apparatus and method including cell primitive for unstructured volume rendering. For example, one embodiment of an apparatus comprises: a ray generator to generate a plurality of rays in a first graphics scene; a hierarchical acceleration data structure generator to construct a hierarchical acceleration data structure comprising a plurality of hierarchically arranged nodes including leaf nodes and inner nodes; traversal circuitry to traverse one or more of the rays through the hierarchical acceleration data structure; unstructured volume intersection circuitry to intersect a ray with an unstructured volume primitive within a leaf node of the hierarchical acceleration data structure, the unstructured volume intersection circuitry to determine multiple intersection hits between a ray and an unstructured volume primitive.

Abstract: Apparatus and method for a hierarchical beam tracer.

Abstract: Systems, devices, and techniques related to thin form factor head mounted displays and near light field displays are discussed. Such devices may include a display to present elemental images, a primary lens array in an optical path between the display and a viewing zone of a user, the primary lens array to magnify elemental images to a viewing zone, and a secondary array of optical elements between the display and the primary lens array to concentrate elemental images from the display to the primary lens array.

Abstract: Apparatus and method for a hierarchical beam tracer.