Abstract: Methods, apparatus, systems, and articles of manufacture to control an aggressiveness of display panel power savings are disclosed. An example apparatus include a display panel, a display controller to adjust an image to be displayed by the display panel, and a power savings controller to access an image provided to the display controller, execute a machine learning model using the image as an input to generate an aggressiveness value, and provide the aggressiveness value to the display controller, the display controller to adjust the image based on the aggressiveness value.

Abstract: Systems, apparatus, articles of manufacture, and methods are disclosed to generate super-resolution upscaling. An example apparatus to process an image disclosed herein includes interface circuitry to accept input image data with a first resolution, machine readable instructions, and programmable circuitry to at least one of instantiate or execute the machine readable instructions to upscale the input image data based on an upscale factor to generate intermediate image data with a second resolution higher than the first resolution, process the input image data with a neural network to produce neural network output data with a number of channels per pixel that is based on the upscale factor, combine the intermediate image and the neural network output data to generate output image data with the second resolution.

Abstract: An apparatus to facilitate partially-frozen neural networks for efficient computer vision systems is disclosed. The apparatus includes a frozen core to store fixed weights of a machine learning model, one or more trainable cores coupled to the frozen core, the one or more trainable cores comprising multipliers for trainable weights of the machine learning model, and wherein the alpha blending layer includes a trainable alpha blending parameter, and wherein the trainable alpha blending parameter is a function of a trainable parameter, a sigmoid function, and outputs of frozen and trainable blocks in a preceding layer of the machine learning model.

Abstract: An apparatus to facilitate partially-frozen neural networks for efficient computer vision systems is disclosed. The apparatus includes a frozen core to store fixed weights of a machine learning model, one or more trainable cores coupled to the frozen core, the one or more trainable cores comprising multipliers for trainable weights of the machine learning model, and wherein the alpha blending layer includes a trainable alpha blending parameter, and wherein the trainable alpha blending parameter is a function of a trainable parameter, a sigmoid function, and outputs of frozen and trainable blocks in a preceding layer of the machine learning model.

Abstract: An apparatus to facilitate partially-frozen neural networks for efficient computer vision systems is disclosed. The apparatus includes a frozen core to store fixed weights of a machine learning model, one or more trainable cores coupled to the frozen core, the one or more trainable cores comprising multipliers for trainable weights of the machine learning model, and wherein the alpha blending layer includes a trainable alpha blending parameter, and wherein the trainable alpha blending parameter is a function of a trainable parameter, a sigmoid function, and outputs of frozen and trainable blocks in a preceding layer of the machine learning model.

Abstract: An example apparatus for processing images includes a trainable vision scaler to receive an image. The trainable vision scaler is to generate output including a feature map or an enhanced image based on the image. The trainable vision scaler is to transmit the output to a computer vision network. The computer vision network is trained to perform a computer vision task using the output.

Abstract: An example apparatus for processing images includes a hybrid infinite impulse response-finite impulse response (IIR-FIR) convolution block to receive an image and generate processed image information. The hybrid IIR-FIR convolution block includes a vertical infinite impulse response (IIR) component to approximate a vertical convolution when processing the image.

Abstract: Methods, apparatus, systems, and articles of manufacture to control an aggressiveness of display panel power savings are disclosed. An example apparatus include a display panel, a display controller to adjust an image to be displayed by the display panel, and a power savings controller to access an image provided to the display controller, execute a machine learning model using the image as an input to generate an aggressiveness value, and provide the aggressiveness value to the display controller, the display controller to adjust the image based on the aggressiveness value.

Abstract: An apparatus to facilitate partially-frozen neural networks for efficient computer vision systems is disclosed. The apparatus includes a frozen core to store fixed weights of a machine learning model, one or more trainable cores coupled to the frozen core, the one or more trainable cores comprising multipliers for trainable weights of the machine learning model, and wherein the alpha blending layer includes a trainable alpha blending parameter, and wherein the trainable alpha blending parameter is a function of a trainable parameter, a sigmoid function, and outputs of frozen and trainable blocks in a preceding layer of the machine learning model.

Abstract: A mechanism is described for facilitating automatic tuning of image signal processors using reference images in image processing environments, according to one embodiment. A method of embodiments, as described herein, includes one or more processors to: receive images associated with one or more scenes captured by one or more cameras; access tuning parameters associated with functionalities within an image signal processor (ISP) pipeline; generate reference images based on the tuning parameters, wherein a reference image is associated with an image for each functionality within the ISP pipeline; and automatically tune the ISP pipeline based on selection of one or more of the reference images for one or more of the images for one or more of the functionalities.

Abstract: An example apparatus for processing images includes a hybrid infinite impulse response—finite impulse response (IIR-FIR) convolution block to receive an image and generate processed image information. The hybrid IIR-FIR convolution block includes a vertical infinite impulse response (IIR) component to approximate a vertical convolution when processing the image.

Abstract: An example apparatus for processing images includes a trainable vision scaler to receive an image. The trainable vision scaler is to generate output including a feature map or an enhanced image based on the image. The trainable vision scaler is to transmit the output to a computer vision network. The computer vision network is trained to perform a computer vision task using the output.

Abstract: A mechanism is described for facilitating automatic tuning of image signal processors using reference images in image processing environments, according to one embodiment. A method of embodiments, as described herein, includes one or more processors to: receive images associated with one or more scenes captured by one or more cameras; access tuning parameters associated with functionalities within an image signal processor (ISP) pipeline; generate reference images based on the tuning parameters, wherein a reference image is associated with an image for each functionality within the ISP pipeline; and automatically tune the ISP pipeline based on selection of one or more of the reference images for one or more of the images for one or more of the functionalities.

Abstract: A spatially varying PSF may be applied in a camera simulator by multiplying a fixed weight map by its impact region. Next, Fast Fourier Transform (FFT) both IWk and Ak, multiply the FFT results element by element and do an inverse FFT (IFFT) to bring the results back to spatial domain. The output image is exactly the same as the outcome of direct approach with the same interpolation method for spatially varying PSF. However, the operation now will be significantly faster in some embodiments.