The method includes generating, for each of a plurality of original images, a first artificially degraded image by applying a first image-artifact-generation logic on each of the original images; and generating the program logic by training an untrained version of a first machine-learning logic that encodes a first artifacts-removal logic on the original images and their respectively generated first degraded images; and returning the trained first machine-learning logic as the program logic or as a component thereof. The first image-artifact-generation logic is A) an image-acquisition-system-specific image-artifact-generation logic or B) a tissue-staining-artifact-generation logic.

A neural network model training apparatus for enhancing image detail is provided. The apparatus includes a memory and at least one processor configured to obtain a low quality input image patch and a high quality input image patch, obtain a low quality output image patch by inputting the low quality input image patch to a first neural network model, obtain a high quality output image patch by inputting the high quality input image patch to a second neural network model, and train the first neural network model based on a loss function set to reduce a difference between the low quality output image patch and the high quality input image patch, and a difference between the high quality output image patch and the high quality input image patch. The second neural network model is identical to the first neural network model.

Provided are embodiments for a method for performing colorization of scans. The method includes analyzing a scanner, a scan of an environment to identify one or more patterns within the scan, and obtaining a subset of colorization data of the environment. The method also includes predicting colors for the one or more patterns in the scan based on the subset of colorization data, and assigning the predicted colors to the one or more patterns in the scan to generate a colorized scan. The method includes displaying the colorized scan, wherein the colorized scan combines the scan and the predicted colorization data by assigning the predicted colorization data to the one or more patterns in the scan. Also provided are embodiments for a system for performing the colorization of scans.

A method of improving image quality of a stream of input images is described. The stream of input images, including a current input image, is received. One or more target objects, including a first target object, are identified spatio-temporally within the stream of input images. The one or more target objects are tracked spatio-temporally within the stream of input images. The current input image is segmented into i) a foreground including the first target object, and ii) a background. The foreground is processed to have improved image quality in the current input image. Processing of the foreground further comprises processing the first target object using a same processing technique as for a prior input image of the stream of input images based on the tracking of the first target object. The background is processed differently from the foreground. An output image is generated by merging the foreground with the background.

A method, apparatus, and non-transitory computer-readable medium for adaptive neural image compression by meta-learning using substitute QF settings, which includes generating one or more substitute quality factors via a plurality of iterations using the original quality factors, wherein the substitute quality factors are a modified version of the original quality factors and are associated with a single instance of neural network loop filtering model. The approach may further include determining a neural network based loop filter comprising neural network based loop filter parameters and a plurality of layers, wherein the neural network based loop filter parameters include shared parameters and adaptive parameters, and may further include generating enhanced video data, based on the one or more substitute quality factors and the input video data, using the neural network based loop filter.

Graphic arts software has evolved to provide users with a variety of mark making tools to simulate different brushes, papers, and applied media such as ink, chalk, watercolour, spray paint and oils. However, in many instances the marks rendered appear unnatural and artificial despite the software's goal being to simulate as realistically. Accordingly, it would be beneficial to provide either users or the software application with a mechanism to remove or reduce artifacts indicative of artificial generation, e.g. rapid transitions. Further, in many instances the graphic images generated and/or manipulated refer to imagined environments or have elements that are physical in nature. Accordingly, it would be beneficial to provide users with a range of mark making tools that represent marks made by mark making tools comprising multiple elements following physical laws.

A detection system method of color balancing an image includes receiving an image of a test area of a pad which includes a color of a reaction between a test substance and at least one reagent on the test area of the pad, an alignment code having detection system identification information, at least one color calibration block indicia for aligning with a camera as the image is being captured, and test identification information for analyzing the test substance during a colorimetric analysis. The method further includes collecting an array of pixels of RGB values for each pixel in the image, evaluating a captured color of the at least one color calibration block in the image, and performing the colorimetric analysis on the reaction between the test substance and the at least one reagent.

An endoscope system includes a light source unit, an image sensor, an image acquisition unit, a first image generation unit, a second image generation unit, and a region discrimination unit. The light source unit emits a plurality of types of illumination light beams with different wavelengths. The image acquisition unit acquires images corresponding to the respective illumination light beams. The first image generation unit generates a first image (white light image) serving as a base of a display image. The second image generation unit generates a second image (bright/dark region discrimination image or the like), using at least one image having a different corresponding wavelength from that of the image used for the generation of the first image. The region discrimination unit discriminates the regions in the observation target, using the second image.

A system comprises an encoder configured to compress attribute information and/or spatial for a point cloud and/or a decoder configured to decompress compressed attribute and/or spatial information for the point cloud. To compress the attribute and/or spatial information, the encoder is configured to convert a point cloud into an image based representation. Also, the decoder is configured to generate a decompressed point cloud based on an image based representation of a point cloud. A closed-loop color conversion process is used to improve compression while taking into consideration distortion introduced throughout the point cloud compression process.

Implementations of the present disclosure include receiving a training image, providing a hash pattern that is representative of the training image, applying a plurality of filters to the training image to provide a respective plurality of filtered training images, identifying a filter to be associated with the hash pattern based on the plurality of filtered training images, and storing a mapping of the filter to the hash pattern within a set of mapping in a data store.