Systems and methods are provided for initiating transfer of image data corresponding to at least one predetermined level of an image pyramid comprising higher resolution to a graphic processing unit (GPU) of the computing device, calculating, by the central processing unit (CPU) of the computing device, optical flow of at least one predetermined coarse level of the image pyramid, transferring, by the CPU of the computing device, the calculated optical flow of the at least one predetermined coarse level of the image pyramid to the GPU, calculating, by the GPU of the computing device, the optical flow of the at least one predetermined level of the image pyramid comprising higher resolution, and outputting, by the GPU of the computing device, the optical flow of the image data.

The present disclosure provides a method of training a generative adversarial network. The method includes iteratively enhancing a first noise input in a generative network to generate a first output image; iteratively enhancing a second noise input in the generative network to generate a second output image; transmitting the first output image and a second reference image to a discriminative network, the second reference image corresponding to the first reference image and having a higher resolution than the first reference image; obtaining a first score from the discriminative network based on the second reference image, and a second score from the discriminative network based on the first output image; calculating a loss function of the generative network based on the first score and the second score; and adjusting at least one parameter of the generative network to lower the loss function of the generative network.

Methods and systems are provided for accurately filling holes, regions, and/or portions of high-resolution images using guided upsampling during image inpainting. For instance, an image inpainting system can apply guided upsampling to an inpainted image result to enable generation of a high-resolution inpainting result from a lower-resolution image that has undergone inpainting. To allow for guided upsampling during image inpainting, one or more neural networks can be used. For instance, a low-resolution result neural network (e.g., comprised of an encoder and a decoder) and a high-resolution input neural network (e.g., comprised of an encoder and a decoder). The image inpainting system can use such networks to generate a high-resolution inpainting image result that fills the hole, region, and/or portion of the image.

Systems, apparatus, and methods for super-resolution of non-uniform spatial blur. Non-uniform spatial blur presents unique challenges for conventional neural network processing. Existing implementations attempt to handle super-resolution with a “brute force” optimization. Various embodiments of the present disclosure subdivide the super-resolution function into sub-steps. “Unfolding” super-resolution into smaller closed-form functions allows for operation generic plug-and-play convolutional neural network (CNN) logic. Additionally, each step can be optimized with its own step-specific hyper parameters to improve performance.

Systems and methods in accordance with embodiments of the invention are disclosed that use super-resolution (SR) processes to use information from a plurality of low resolution (LR) images captured by an array camera to produce a synthesized higher resolution image. One embodiment includes obtaining input images using the plurality of imagers, using a microprocessor to determine an initial estimate of at least a portion of a high resolution image using a plurality of pixels from the input images, and using a microprocessor to determine a high resolution image that when mapped through the forward imaging transformation matches the input images to within at least one predetermined criterion using the initial estimate of at least a portion of the high resolution image. In addition, each forward imaging transformation corresponds to the manner in which each imager in the imaging array generate the input images, and the high resolution image synthesized by the microprocessor has a resolution that is greater than any of the input images.

Enhancing color reproduction of an image in an upscaling process, the method comprising: converting RGB-formatted data into luminance channel formatted data and color channel formatted data; converting RGB-predicted data into luminance channel predicted data and a color channel predicted data; computing a first loss between the RGB-formatted data and the RGB-predicted data; computing a second loss between the color channel formatted data and the color channel predicted data; and outputting a weighted average value of the first loss and the second loss to enhance the color reproduction of the image.

Examples of methods for image enhancement are described. In some examples, a method includes segmenting an image into an object region and a background region. In some examples, the image has a first resolution. In some examples, the method includes generating, using a first machine learning model, an enhanced object region with a second resolution that is greater than the first resolution. In some examples, the first machine learning model has been trained based on object landmarks. In some examples, the method includes generating, using a second machine learning model, an enhanced background region with a third resolution that is greater than the first resolution. In some examples, the method includes combining the enhanced object region and the enhanced background region to produce an enhanced image.

A system and a method for super-resolution image processing in remote sensing are disclosed. One or more sets of multi-temporal images with an input resolution and one or more first target images with a first output resolution are generated from one or more data sources. The first output resolution is higher than the input resolution. Each set of multi-temporal images is processed to improve an image match in the corresponding set of multi-temporal images. The one or more sets of multi-temporal images are associated with the one or more first target images to generate a training dataset. A deep learning model is trained using the training dataset. The deep learning model is provided for subsequent super-resolution image processing.

An image processing device is provided, which includes an image capture circuit and a processor. The image capture circuit is configured to capture a low-resolution image. The processor is connected to the image capture circuit and executes a super-resolution model (SRM), wherein the SRM includes multiple neural network blocks, and the processor is configured to perform the following operations: generating a super-resolution image from the low-resolution image by using the multiple neural network blocks, where one of the multiple neural network blocks includes a spatial attention model (SAM) and a channel attention model (CAM), the CAM is concatenated after the SAM, and the SAM and the CAM are configured to enhance a weight of a region in the super-resolution image, which is covered by a region of interest in the low-resolution image. In addition, an image processing method is also disclosed herein.

A method for structure simulation for super-resolution fluorescence microscopy, the method including receiving a first image having a first resolution, which is indicative of a distribution of fluorophores; applying a Markov model to the fluorophores to indicate an emission state of the fluorophores; generating a plurality of second images, having the first resolution, based on the first image and the Markov model; adding DC background to the plurality of second images to generate a plurality of third images, having the first resolution; downsampling the plurality of third images to obtain a plurality of fourth images, which have a second resolution, lower than the first resolution; and generating a time-series, low-resolution images by adding noise to the plurality of fourth images. The time-series, low-resolution images have the second resolution.