Abstract: Systems and methods for generating images using hybrid sampling include obtaining a noisy image and generating a first denoised image during a first reverse diffusion phase using a diffusion neural network. The first denoised image is generated based on a first sampler that uses a first sampling density during at least a portion of the first reverse diffusion phase. Subsequently, a second denoised image is generated based on the first denoised image during a second reverse diffusion phase using the diffusion neural network. The second denoised image is generated based on a second sampler that uses a second sampling density different from the first sampling density during at least a portion of the second reverse diffusion phase.

Abstract: The present disclosure relates to a computer implemented method for detecting artifacts in infrared (IR) illuminated IR images. Artifacts are separated from real objects by analyzing results of regression line fits to histograms of pixel values. Artifacts will have smooth transition gradients and therefore will show smaller deviations of the regression line fit to the histogram data.

Abstract: An inspection system may perform an inspection recipe by receiving reference SHG images of a reference structure based on a scan of the reference structure with an illumination beam and collecting second harmonic generation (SHG) light in response to the illumination beam, where the reference structure includes a multilayer structure including one or more inversion-symmetric materials. The system may further receive test SHG images of a test structure based on a scan of the test structure by illuminating the test structure with the illumination beam and collecting the SHG light in response to the illumination beam, where the test structure and the reference structure have a common design. The system may further identify defects in the test structure by comparing the test and reference SHG images.

Abstract: An embodiment of the present disclosure provides a three-dimensional image generation method, which is performed by a server and is capable of domain adaptation, including generating N target images corresponding to a second domain by converting styles of previously collected N source images corresponding to a first domain according to instructions of an input text, selecting only a target image that satisfies a preset condition among the N target images, and generating multiple three-dimensional images corresponding to a specific domain through certain noise data and a preset camera pose parameter by training a three-dimensional generation model, which is previously built, by using the selected target image.

Abstract: Various implementations disclosed herein include devices, systems, and methods that track a movement of an input device. For example, an example process may include determine a pose of a tracking device in a physical environment based on first sensor data from an image sensor. The process then may receive, from the tracking device, first positional data corresponding to a first relative positioning between the tracking device and an input device in the physical environment, where the first positional data is determined based on second sensor data obtained via a sensor on the tracking device. The process then may track movement of the input device in the physical environment based at least in part on the first positional data and the pose of the tracking device. The process then may determine an input for the electronic device based at least in part on tracking the movement of the input device.

Abstract: Classification of images is inherently a semi-supervised classification problem. Often, the labeled pixels and the unlabeled pixels in the image may have different distribution. Hence classification accuracy of such images is affected. The present disclosure proposes an umbrella framework for semi-supervised learning that considers the domains shifts in labeled and unlabeled pixels. The method proposed a two way optimization solution using deep learning models based on spectral features, spatial features, and fused spectral-spatial features. The model is trained in such a way that it is not only trained on the correct class of pixel but also on the source category of the pixel, for example, labeled pixel or unlabeled pixel. The error in the pixel class is minimized, whereas the error in the source category is encouraged simultaneously.

Abstract: Devices, methods, and non-transitory computer readable media are disclosed herein to repair or mitigate the appearance of unwanted reflection artifacts in captured video image streams. These unwanted reflection artifacts often present themselves as brightly-colored spots that reflect the shape of a bright light source in the captured image. These artifacts, also referred to herein as “green ghosts” (due to often having a greenish tint), are typically located in regions of the captured images where there is not actually a bright light source located in the image. In fact, such unwanted reflection artifacts often present themselves on the image sensor across the principal point of the lens from where the actual bright light source in the captured image is located. Such devices, methods and computer readable media may be configured to detect, track, and repair such unwanted reflection artifacts in an intelligent fashion, e.g., leveraging images captured with varying exposure settings.

Abstract: A method, system, and article is directed to automatic content-dependent image processing algorithm selection.

Abstract: This system for training an operation determination model for a medical instrument control device generates training data by means of a reinforcement learning model, and, using the training data, can train an operation determination model configured to output information associated with operational commands for a driving unit that transports medical instruments.

Abstract: A document creation support apparatus comprising at least one processor, wherein the processor is configured to: extracts regions having one or more preset physical features from a medical image, and generates a comment on findings using a disease name associated with a physical feature of at least one of the extracted regions.

Abstract: Embodiments of the present application provide an image enhancement method, a chip, and an image acquisition device. The method comprises: storing, by a main processor, a preset number of Raw image frames to be processed currently acquired from a sensor in a first off-chip memory, into the on-chip memory; performing, by a first neural network processor, image fusion on a preset number of Raw image frames to be fused currently obtained based on the preset number of Raw image frames to be processed currently in the on-chip memory based on a preset image fusion network, to obtain a fused Raw image frame, and storing it into the on-chip memory; sending, by the main processor to an ISP chip, a target Raw image frame to be sent currently obtained based on the fused Raw image frame in the on-chip memory.

Abstract: Systems, methods, models, and training data for models are discussed, for determining vehicle positioning, and in particular identifying tailgating. Simulated training images showing vehicles following other vehicles, under various conditions, are generated using a virtual environment. Models are trained to determine following distance between two vehicles. Trained models are used to in detection of tailgating, based on determined distance between two vehicles. Results of tailgating are output to warn a driver, or to provide a report on driver behavior.

Abstract: Methods, systems, and computer readable media are disclosed for characterizing the porosity of a microspheric material, training a classifier model for classifying spatially-contiguous image regions of backscatter electron scanning electron microscopy (BSE-SEM) images of a microspheric material according to the particle composition of the image regions, and characterizing the elemental composition of a microspheric material. The methods include: receiving image data representative of a microscopic images of a sample microspheric material; segmenting the image data into a plurality of spatially-contiguous image regions; classifying, by a trained machine-learning model, each of the plurality of spatially-contiguous image regions; and characterizing the microspheric material. The disclosure also relates to compositions for use as an FCC catalyst comprising microspheres which comprise alumina and/or clay and/or a zeolite.

Abstract: A method includes segmenting a region of interest in an anatomical region in both a source imaging data and a destination imaging data, wherein different regions of the region of interest are labeled with different segmentation masks. The method includes selecting a region from the different regions from the source imaging data and spatially matching the region to a corresponding region in the destination imaging data. The method includes determining a spatial intersection between the region and the corresponding region. The method includes utilizing an intersection mask to crop a first portion of the region from the source imaging data and utilizing the intersection mask to remove a second portion of the destination imaging data in the corresponding region. The method includes adding the first portion of the region from the source imaging data into the destination imaging data where the second portion was removed.

Abstract: Systems and methods for automatically extracting one or more salient images from a surgical video stream are described. A plurality of records including annotated images from recorded surgical procedures are used as training data to generate an image extraction machine learning model. Features, extracted from the training data, are used as inputs to the image extraction machine learning model in a training phase, which outputs salient images. After training, features extracted from the surgical video stream are input into the trained image extraction machine learning model to output the one or more salient images from the surgical video stream.

Abstract: A patch-based deblurring method to deblur images blurred in a non-uniform manner (e.g., motion blur or camera shake) uses a modified total-variation (TV) minimization algorithm to make a network specifically designed to handle non-uniform blur.

Abstract: A medical image processing method includes the following steps. A first medical image about a first patient under a first examination condition is obtained. A second medical image about the first patient under a second examination condition is obtained. A first label corresponding to the first medical image is collected. The first label marks a lesion within the first medical image. A transformation function between the first medical image and the second medical image is calculated by aligning the first medical image with the second medical image. The transformation function is applied to convert the first label into a second label corresponding to the second medical image.

Abstract: The present invention relates to a method (1), resp. a device, system and computer-program product, for material decomposition of spectral imaging projection data. The method comprises receiving (2) projection data acquired by a spectral imaging system and reducing (3) noise in the projection data by combining corresponding spectral values for different projection rays to obtain noise-reduced projection data. The method comprises applying (6) a first projection-domain material decomposition algorithm to the noise-reduced projection data to obtain a first set of material path length estimates, and applying (7) a second projection-domain material decomposition algorithm to the projection data to obtain a second set of material path length estimates. The second projection-domain material decomposition algorithm comprises an optimization that penalizes a deviation between the second set of material path length estimates being optimized and the first set of material path length estimates.

Abstract: The present invention concerns a method for determining the solar distribution in an area, the including, a phase for collecting data to form a training database, a phase for training a model on the basis of the training database to obtain a trained model, the input of the trained model being an image of an area seen from the sky and the output being a global cartography of the irradiance projected on each surface of the area imaged on the input image, and a phase for operating the trained model. The phase for operating the trained models includes, a step of receiving an image of an area seen from the sky, and a step of determining by the trained model a global cartography of the irradiance projected on each surface of the area imaged on the received image.

Abstract: An input receiving unit receives a designation input of a user for a medical image displayed on a first display screen of a display. An image selection unit acquires selected images selected from a plurality of medical images based on a designated image category that is a category assigned to a designated image and a non-designated image category that is a category assigned to a non-designated image. The selected images are displayed in a list on a second display screen of the display.