An object (100) is illuminated sequentially using at least two illumination geometries (110-1, 110-2). An intensity image of the object (100) is captured for each one of the at least two illumination geometries (110-1, 110-2). The intensity images are combined for producing a results image. Combining is carried out in such a way that the results image satisfies a predetermined optimization criterion. By way of example, the optimization criterion may relate to an image contrast, an edge steepness or an image sharpness. Optimization may be carried out with a spatial resolution.

In order to solve the problems described above, the present invention employs a PSF restoring means and an image restoring means, implemented in software or hardware, for executing a plurality of iterations of real-number-based computations based on Bayse probability theory by using, as input information, a PSF luminance distribution identified according to a degree of degradation of TV video, a luminance distribution of a degraded image constituted of Y (luminance) components of the TV video, and an estimated luminance distribution of restored-image initial values. With these means, an estimated luminance distribution of a restored image having a maximum likelihood for the luminance distribution of the degraded image is obtained, and the estimated luminance distribution is substituted for the Y components of the TV video obtained by extracting the luminance distribution of the degraded image. Accordingly, TV video that approximates the pre-degradation state is provided substantially in real time.

A system for generating a high resolution (HR) computed tomography (CT) image from a low resolution (LR) CT image is described. The system includes a first generative adversarial network (GAN) and a second GAN. The first GAN includes a first generative neural network (G) configured to receive a training LR image dataset and to generate a corresponding estimated HR image dataset, and a first discriminative neural network (D.sub.Y) configured to compare a training HR image dataset and the estimated HR image dataset. The second GAN includes a second generative neural network (F) configured to receive the training HR image dataset and to generate a corresponding estimated LR image dataset, and a second discriminative neural network (D.sub.X) configured to compare the training LR image dataset and the estimated LR image dataset. The system further includes an optimization module configured to determine an optimization function based, at least in part, on at least one of the estimated HR image dataset and/or the estimated LR image dataset. The optimization function contains at least one loss function. The optimization module is further configured to adjust a plurality of neural network parameters associated with at least one of the first GAN and/or the second GAN, to optimize the optimization function.

A system accesses content structure that includes a first attribute table including a first list of attributes of a first object, and a first mapping including first attribute values. The first list of attributes of the first object also includes a quality attribute indicating a first quality. After a request to modify quality is received, the system searches a plurality of content structures for a suitable second content structure that comprises a second attribute table including a second list of attributes of a second object. The suitable content structure has another attribute that matches a corresponding attribute of the first list of attributes of the first object and a quality attribute indicating a second quality. The system modifies the first attribute table to include the second list of attributes of the second object. In this way content is generated that is of higher or lower quality than the original content.

An embodiment method for converting an initial digital image into a converted digital image, electronic chip, system and computer program product are disclosed, the initial digital image comprising a set of pixels, the pixels being associated respectively with colors, the initial digital image being acquired by an acquisition device, and the converted digital image able to be used by a neural network. The embodiment method comprises redimensioning of the initial digital image in order to obtain an intermediate digital image, the redimensioning being carried out by a reduction in the number of pixels of the initial image, modification of a format of one of the pixels of the intermediate digital image in order to obtain a converted digital image, the modification being carried out, after the redimensioning, by increasing the number of bits used to represent the color of the pixel.

In one embodiment, a method includes accessing first-resolution images corresponding to frames of a video, computing a motion vector based on a first-resolution image of a first frame in the video and a first-resolution image of a second frame in the video, generating a second-resolution warped image associated with the second frame by using the motion vector to warp a second-resolution reconstructed image associated with the first frame, generating a second-resolution intermediate image associated with the second frame based on the first-resolution image associated with the second frame, computing adjustment parameters by processing the first-resolution image associated with the second frame and the second-resolution warped image associated with the second frame using a machine-learning model, and adjusting pixels of the second-resolution intermediate image associated with the second frame based on the adjustment parameters to reconstruct a second-resolution reconstructed image associated with the second frame.

A system includes at least one imaging sensor configured to capture images of a target. The system also includes at least one controller configured to generate super-resolution images of the target using the captured images and identify multiple edges of the target using the super-resolution images. The at least one controller is also configured to identify an aimpoint on the target based on the identified edges of the target. In addition, the at least one controller is configured to update the aimpoint on the target as the target moves over time. The system may further include a high-energy laser (HEL) configured to generate an HEL beam that is directed towards the target, and the at least one controller may be configured to adjust one or more optical devices to direct the HEL beam at the identified aimpoint on the target.

Disclosed is an image processing apparatus. The present image processing apparatus comprises: an input unit for inputting an image; and a processor for shrinking the inputted image to a predetermined ratio, extracting a visual feature from the shrunken image, performing an image quality enhancement process reflecting the extracted visual feature in the inputted image, repeatedly performing, for a predetermined number of times, the shrinking, the extracting, and the image quality enhancement process on the image that has undergone the image quality enhancement process. The present disclosure relates to an artificial intelligence (AI) system and an application thereof that simulate the functions of a human brain, such as recognition, judgment, etc., by using a machine learning algorithm such as deep learning, etc.

This application provides a method for generating a high-resolution picture performed by a computer device. The method includes: acquiring at least one deep neural network model; acquiring a low-resolution picture; determining a corresponding deep neural network model according to the low-resolution picture; and converting the low-resolution pictures into a high-resolution picture through the deep neural network model, the deep neural network model including a plurality of non-linear conversion convolution layers that alternately use different parameter matrices as convolution template parameters.

The present invention discloses a disparity estimation optimization method based on upsampling and exact rematching, which conducts exact rematching within a small range in an optimized network, improves previous upsampling methods such as neighbor interpolation and bilinear interpolation for disparity maps or cost maps, and works out a propagation-based upsampling method by the way of network so that accurate disparity values can be better restored from disparity maps in the upsampling process.