Abstract: An apparatus to facilitate combined denoising and upscaling network with importance sampling in a graphics environment is disclosed. The apparatus includes set of processing resources including circuitry configured to: receive, at an input of a density map neural network, a sampled signal of a current frame and a reconstructed sample of the current frame; output, from the density map neural network, a prediction of a density map of samples based on the input of the current frame; provide the density map of samples to a sampler; reproject the density map of samples to a next frame; and apply the reprojected density map of samples to the next frame to generate a next sampled signal.

Abstract: Systems, apparatuses and methods may provide for technology that selects a subset of linear layers from a plurality of linear layers in a pre-trained artificial intelligence (AI) model, wherein a quantization error of the subset of linear layers exceeds an error threshold. For each linear layer in the subset of linear layers, the technology solves a singular value decomposition (SVD) approximation, generates a first adapter layer and a second adapter layer based on the SVD decomposition, wherein the first adapter layer and the second adapter layer include weight matrices having a first dimension that is less than a first rank threshold and a second dimension that is greater than a second rank threshold, and determines an inference output based on the linear layer, the first adapter layer and the second adapter layer.

Abstract: One embodiment provides a graphics processor comprising a set of processing resources configured to perform a supersampling anti-aliasing operation via a mixed precision convolutional neural network. The set of processing resources include circuitry configured to receive, at an input block of a neural network model, a set of data including previous frame data, current frame data, jitter offset data, and velocity data, pre-process the set of data to generate pre-processed data, provide pre-processed data to a feature extraction network of the neural network model and an output block of the neural network model, process the first pre-processed data at the feature extraction network via one or more encoder stages and one or more decoder stages, output tensor data from the feature extraction network to the output block, and generate an anti-aliased output frame via the output block based on the current frame data and the tensor data output from the feature extraction network.

Abstract: One embodiment provides a graphics processor comprising a set of processing resources configured to perform a supersampling anti-aliasing operation via a mixed precision convolutional neural network. The set of processing resources include circuitry configured to receive, at an input block of a neural network model, a set of data including previous frame data, current frame data, jitter offset data, and velocity data, pre-process the set of data to generate pre-processed data, provide pre-processed data to a feature extraction network of the neural network model and an output block of the neural network model, process the first pre-processed data at the feature extraction network via one or more encoder stages and one or more decoder stages, output tensor data from the feature extraction network to the output block, and generate an anti-aliased output frame via the output block based on the current frame data and the tensor data output from the feature extraction network.

Abstract: An apparatus including a dielectric lens and a feeding array having feeding elements at different positions. The apparatus also including circuitry configured to simultaneously operate one feeding element of a first group of feeding elements and one feeding element of a second group of feeding elements.

Abstract: An apparatus to facilitate trainable visual quality metrics for measuring rendering quality in a graphics environment is disclosed. The apparatus includes a set of processing resources configured to perform a supersampling anti-aliasing operation, the set of processing resources including circuitry to: receive, at a trained visual quality neural network, a sampled signal for visual quality measurement, wherein the sampled signal comprises a reference image of current frame of a video, and wherein the reference image comprising an original image prior to a reconstruction process being applied to the original image; generate, by the trained visual quality neural network, a prediction of a visual quality score for the reconstructed image corresponding to the sampled signal; and notify, by the trained visual quality neural network, a visual quality measurement system of the prediction of the visual quality score for the reconstructed image.

Abstract: An apparatus to facilitate augmenting temporal anti-aliasing with a neural network for history validation is disclosed. The apparatus includes a set of processing resources configured to perform augmented temporal anti-aliasing (TAA), the set of processing resources including circuitry configured to: receive, at a history validation neural network, inputs for a current pixel of a current frame and a reprojected pixel corresponding to the current pixel, the reprojected pixel originating from history data of the current frame; generate, using an output of the history validation neural network, a validated color for the current pixel based on current color data corresponding to the current pixel and history color data corresponding to the reprojected pixel; render an output frame using the validated color; and add the output frame to the history data.

Abstract: An apparatus to facilitate combined denoising and upscaling network with importance sampling in a graphics environment is disclosed. The apparatus includes set of processing resources including circuitry configured to: receive, at an input of a density map neural network, a sampled signal of a current frame and a reconstructed sample of the current frame; output, from the density map neural network, a prediction of a density map of samples based on the input of the current frame; provide the density map of samples to a sampler; reproject the density map of samples to a next frame; and apply the reprojected density map of samples to the next frame to generate a next sampled signal.

Abstract: Apparatus comprising a plurality of antenna devices and a feeding device, wherein said feeding device is configured to receive a first input signal, to generate a plurality of first output signals by power dividing said first input signal, and to provide said plurality of first output signals to said plurality of antenna devices, wherein two or more of said antenna devices comprise a first antenna element for receiving at least a portion of said plurality of first output signals as a second input signal, a signal processing device configured to determine a second output signal depending on said second input signal by at least temporarily modifying a phase and/or an amplitude of said second input signal or a signal derived from said second input signal, and a second antenna element, wherein said signal processing device is configured to provide said second output signal to said second antenna element.

Abstract: Apparatus comprising a plurality of antenna devices and a feeding device, wherein said feeding device is configured to receive a first input signal, to generate a plurality of first output signals by power dividing said first input signal, and to provide said plurality of first output signals to said plurality of antenna devices, wherein two or more of said antenna devices comprise a first antenna element for receiving at least a portion of said plurality of first output signals as a second input signal, a signal processing device configured to determine a second output signal depending on said second input signal by at least temporarily modifying a phase and/or an amplitude of said second input signal or a signal derived from said second input signal, and a second antenna element, wherein said signal processing device is configured to provide said second output signal to said second antenna element.

Abstract: Methods and apparatus are presented for determining a position of a GNSS rover antenna from observations collected at the antenna over multiple epochs from satellite signals of multiple GNSS, wherein the observation data of each GNSS has a distinct data format. The observation data of each GNSS are presented in a generic GNSS data format, which differs from the distinct data format of the GNSS, to obtain a set of generic data. A set of difference data is prepared representing differences between the converted observation data and the generic data. When at least four satellites are tracked, the generic data of the tracked satellites of multiple GNSS are used to compute a standalone antenna position. When at least five satellites are tracked, the generic data of the tracked satellites of multiple GNSS are used to compute a real-time kinematic antenna position.

Abstract: Methods and apparatus are presented for determining position a GNSS rover antenna from single-frequency observations of GNSS signals collected at the antenna over multiple epochs and from correction data for at least one of the epochs. Coded raw data prepared from the single-frequency observations in a binary format are obtained and decoded to obtain decoded raw data. The decoded raw data are used to construct multiple epochs of measurement data of time, range and phase. Correction data are obtained for at least one of the epochs. The measurement data are processed with the correction data in a realtime kinematic positioning engine to obtain a position estimate for each of a plurality of epochs.

Abstract: Methods and apparatus are presented for determining a position of a GNSS rover antenna from observations collected at the antenna over multiple epochs from satellite signals of multiple GNSS, wherein the observation data of each GNSS has a distinct data format. The observation data of each GNSS are presented in a generic GNSS data format, which differs from the distinct data format of the GNSS, to obtain a set of generic data. A set of difference data is prepared representing differences between the converted observation data and the generic data. When at least four satellites are tracked, the generic data of the tracked satellites of multiple GNSS are used to compute a standalone antenna position. When at least five satellites are tracked, the generic data of the tracked satellites of multiple GNSS are used to compute a real-time kinematic antenna position.

Abstract: Methods and apparatus are presented for determining position a GNSS rover antenna from single-frequency observations of GNSS signals collected at the antenna over multiple epochs and from correction data for at least one of the epochs. Coded raw data prepared from the single-frequency observations in a binary format are obtained and decoded to obtain decoded raw data. The decoded raw data are used to construct multiple epochs of measurement data of time, range and phase. Correction data are obtained for at least one of the epochs. The measurement data are processed with the correction data in a realtime kinematic positioning engine to obtain a position estimate for each of a plurality of epochs.

Abstract: A technique of accurately determining the relative position of two points using carrier phase information from receivers capable of making code and carrier phase measurements on the L1 and L2 frequencies of signals from either or both GPS and GLONASS satellites. These signals are processed by a receiving system to determine relative position, for the purpose of surveying or otherwise, with the accuracy of carrier phase measurements being obtained. Signal processing similar to that used in existing GPS carrier phase based relative positioning receivers is used with GLONASS signals as well, with a modification that takes into account the unique and different frequencies of the signals from individual GLONASS satellites. Surface acoustic wave (“SAW”) filters are also employed in an intermediate frequency receiver section in order to avoid imparting different delays to the GLONASS signals of different frequencies.

Abstract: A technique of accurately determining the relative position of two points using carrier phase information from receivers capable of making code and carrier phase measurements on the L1 and L2 frequencies of signals from either or both GPS and GLONASS satellites. These signals are processed by a receiving system to determine relative position, for the purpose of surveying or otherwise, with the accuracy of carrier phase measurements being obtained. Signal processing similar to that used in existing GPS carrier phase based relative positioning receivers is used with GLONASS signals as well, with a modification that takes into account the unique and different frequencies of the signals from individual GLONASS satellites. Surface acoustic wave ("SAW") filters are also employed in an intermediate frequency receiver section in order to avoid imparting different delays to the GLONASS signals of different frequencies.