Abstract: A system and method for white balancing a digital image. The method including downsampling the digital image to generate a downsampled image; processing the downsampled image with a plurality of preset white balance settings to generate a plurality of white balanced downsampled images; processing the input image at a fixed white balanced setting to produce an initial image; inputting the white balanced downsampled images to a deep neural network to generate a weighting map, the weighting map including weights of the preset white balance settings at windows of the downsampled images; generating a white balanced output image by applying the weighting map to the initial image; and outputting the white balanced output image.

Abstract: A system and method of determining synthetic dual-pixel data, performing deblurring, predicting dual pixel views, and view synthesis. The method including: receiving an input image; determining synthetic dual-pixel data using a trained artificial neural network with the input image as input to the trained artificial neural network, the trained artificial neural network includes a latent space encoder, a left dual-pixel view decoder, and a right dual-pixel view decoder; and outputting the synthetic dual-pixel data. In some cases, determination of the synthetic dual-pixel data can include performing reflection removal, defocus deblurring, or view synthesis.

Abstract: Systems and methods for sensor-independent illuminant determination are provided. In one embodiment of the method, the method includes receiving one or more training images in raw-RGB format; generating an input histogram from each of the inputted raw images; generating a learned mapping matrix that map raw images to a learned mapping space by passing the one or more input histograms to a trained first machine learning model; generating one or more mapped images by applying the learned mapping matrix to the one or more training images; generating a mapped histogram from each of the mapped images; and determining the result illuminant by passing the one or more mapped histograms as input into a second machine learning model. A final illuminant for an input image can be determined by applying the result illuminant to the input color space of the input image.

Abstract: A system and method of processing of a captured image to facilitate post-processing modification. The method includes: receiving the captured image; down-sampling the captured image to generate a down-sampled image; passing the captured image through an image processing pipeline to generate an initial output image, the image processing pipeline including performing one or more image processing operations on the passed image based on a set of parameters; iteratively passing, in one or more iterations, the down-sampled image through the image processing pipeline to generate an output down-sampled image in each iteration, each iteration using at least one variation to the set of parameters used by the image processing pipeline. Down-sampling can be used to generate a down-sampled initial output image such that a mapping is determined between the down-sampled initial output image and the respective output down-sampled image. The down-sampled images or the mapping can be stored as metadata.

Abstract: A method of enabling an Open RAN-compatible radio unit (O-RU) to apply different beamforming weights to different physical resource blocks (PRBs) using a single sectionId and a single section extension type includes: specifying a first mode of operation in which flexible sending of beamforming weights from Open RAN-compatible distributed unit (O-DU) to Open RAN-compatible radio unit (O-RU) is provided; and providing, by the O-DU to the O-RU, i) a first parameter specifying the number of bundled physical resource blocks (PRBs) per a set of in-phase/quadrature (I/Q) beamforming weight pairs, each beamforming weight pair comprising an in-phase value and a quadrature value, and ii) a plurality of beamforming weight pairs for a plurality of transceivers associated with each bundle of PRBs. The method provides a new section extension type sent by the O-DU to the O-RU and including a compression parameter for processing or decompressing the beamforming weights.

Abstract: A method of enabling an Open RAN-compatible radio unit (O-RU) to apply different beamforming weights to different physical resource blocks (PRBs) using a single sectionId and a single section extension type includes: specifying a first mode of operation in which flexible sending of beamforming weights from Open RAN-compatible distributed unit (O-DU) to Open RAN-compatible radio unit (O-RU) is provided; and providing, by the O-DU to the O-RU, i) a first parameter specifying the number of bundled physical resource blocks (PRBs) per a set of in-phase/quadrature (I/Q) beamforming weight pairs, each beamforming weight pair comprising an in-phase value and a quadrature value, and ii) a plurality of beamforming weight pairs for a plurality of transceivers associated with each bundle of PRBs. The method provides a new section extension type sent by the O-DU to the O-RU and including a compression parameter for processing or decompressing the beamforming weights.

Abstract: Techniques are described for white balancing an input image by determining a color transformation for the input image based on color transformations that have been computed for training images whose color characteristics are similar to those of the input image. Techniques are also described for generating a training dataset comprising color information for a plurality of training images and color transformation information for the plurality of training images. The color information in the training dataset is searched to identify a subset of training images that are most similar in color to the input image. The color transformation for the input image is then computed by combining color transformation information for the identified training images. The contribution of the color transformation information for any given training image to the combination can be weighted based on the degree of color similarity between the input image and the training image.

Abstract: A method of enabling an Open RAN-compatible radio unit (O-RU) to apply different beamforming weights to different physical resource blocks (PRBs) using a single sectionId and a single section extension type includes: specifying a first mode of operation in which the number of beamforming weights in the section extension type 1 is equal to L*numPrbs, L is the number of TRX and numPrbs is the number of physical resource blocks; signaling, by an Open RAN-compatible distributed unit (O-DU) to the O-RU, the first mode of operation by specifying a value of parameter extLen to be zero, wherein extLen is the length of the section extension in units of 32-bit words; and the O-RU applying the kth beamforming weights (bfwI and bfwQ), k=1, 2, . . . , L*numPrbc in section extension type 1 for TRX j, j=0, 1, . . . , L?1 to the ith PRB, i=1, 2, . . . , numPrbc defined under the sectionId of the C-plane message.

Abstract: A method of enabling an Open RAN-compatible radio unit (O-RU) to apply different beamforming weights to different physical resource blocks (PRBs) using a single sectionId and a single section extension type includes: specifying a first mode of operation in which the number of beamforming weights in the section extension type 1 is equal to L*numPrbs, L is the number of TRX and numPrbs is the number of physical resource blocks; signaling, by an Open RAN-compatible distributed unit (O-DU) to the O-RU, the first mode of operation by specifying a value of parameter extLen to be zero, wherein extLen is the length of the section extension in units of 32-bit words; and the O-RU applying the kth beamforming weights (bfwI and bfwQ), k=1, 2, . . . , L*numPrbc in section extension type 1 for TRX j, j=0, 1, . . . , L?1 to the ith PRB, i=1,2, . . . , numPrbc defined under the sectionId of the C-plane message.

Abstract: Systems and methods for sensor-independent illuminant determination are provided. In one embodiment of the method, the method includes receiving one or more training images in raw-RGB format; generating an input histogram from each of the inputted raw images; generating a learned mapping matrix that map raw images to a learned mapping space by passing the one or more input histograms to a trained first machine learning model; generating one or more mapped images by applying the learned mapping matrix to the one or more training images; generating a mapped histogram from each of the mapped images; and determining the result illuminant by passing the one or more mapped histograms as input into a second machine learning model. A final illuminant for an input image can be determined by applying the result illuminant to the input color space of the input image.

Abstract: Techniques are described for white balancing an input image by determining a color transformation for the input image based on color transformations that have been computed for training images whose color characteristics are similar to those of the input image. Techniques are also described for generating a training dataset comprising color information for a plurality of training images and color transformation information for the plurality of training images. The color information in the training dataset is searched to identify a subset of training images that are most similar in color to the input image. The color transformation for the input image is then computed by combining color transformation information for the identified training images. The contribution of the color transformation information for any given training image to the combination can be weighted based on the degree of color similarity between the input image and the training image.

Abstract: A system for analyzing and processing user input and providing a result based on a predetermined set of color identifiers, the system comprising a first user input, wherein the first user input comprises of one or more digital images, a second user input, wherein the second user input comprises of responses to queries, a white balancing method for removing color casts from the first user input to create a final corrected image of the first user input, a first database for storing a predetermined set of color identifiers, a second database for storing product profiles, and a processor for analyzing the final corrected image of the first user input and the second user input collectively, comparing the final corrected image of the first user input and the second user input collectively to the predetermined set of color identifiers, and providing a color output.

Abstract: A system for analyzing and processing user input and providing a result based on a predetermined set of color identifiers, the system comprising a first user input, wherein the first user input comprises of one or more digital images, a second user input, wherein the second user input comprises of responses to queries, a white balancing method for removing color casts from the first user input to create a final corrected image of the first user input, a first database for storing a predetermined set of color identifiers, a second database for storing product profiles, and a processor for analyzing the final corrected image of the first user input and the second user input collectively, comparing the final corrected image of the first user input and the second user input collectively to the predetermined set of color identifiers, and providing a color output.