Abstract: One embodiment provides a system that facilitates efficient collection of training data. During operation, the system obtains, by a recording device, a first image of a physical object in a scene which is associated with a three-dimensional (3D) world coordinate frame. The system marks, on the first image, a plurality of vertices associated with the physical object, wherein a vertex has 3D coordinates based on the 3D world coordinate frame. The system obtains a plurality of second images of the physical object in the scene while changing one or more characteristics of the scene. The system projects the marked vertices on to a respective second image to indicate a two-dimensional (2D) bounding area associated with the physical object.

Abstract: A method for determining a neural network for correcting optical aberrations includes determining one or more images that are at least partly related to an optical system or the design of an optical system. A neural network is determined on the basis of the determined one or more images in such a way that the determined neural network when applied to an image captured by the optical system outputs an image which has been corrected in relation to one or more optical aberrations.

Abstract: A machine learning device with a processor and a memory, in which the processor receives an image and calculates a feature amount of an object included in the image, the processor identifies a local part from the feature amount and calculates a local identification value, the processor calculates an overall identification value using the local identification value, and the processor generates a classifier using the local identification value and the overall identification value and stores it in the memory.

Abstract: An image processing method comprises obtaining an input image; converting the input image or a feature map of the input image into a plurality of target input images or target feature maps, wherein a resolution of each of the target input images or the target feature maps is smaller than a resolution of the feature map of the input image or the input image, and pixels at the same position in each of the target input images or the target feature maps are of a neighborhood relationship with the input image or the feature map of the input image; processing at least a part of the plurality of target input images or target feature maps by one or more convolution blocks in a convolutional neural network; and increasing a resolution of a feature map output from the one or more convolution blocks in the convolutional neural network.

Abstract: The present disclosure is directed, among other things, to automated systems and methods for analyzing, storing, and/or retrieving information associated with biological objects having irregular shapes. In some embodiments, the systems and methods partition an input image into a plurality of sub-regions based on localized colors, textures, and/or intensities in the input image, wherein each sub-region represents biologically meaningful data.

Abstract: A method and related software are disclosed for processing imagery related to three dimensional models. To display new visual data for select portions of images, an image of a physical structure such as a building with a façade is retrieved with an associated three dimensional model for that physical structure according to common geolocation tags. A scaffolding of surfaces composing the three dimensional model is generated and regions of the retrieved image are registered to the surfaces of the scaffolding to create mapped surfaces for the image. New image data such as texture information is received and applied to select mapped surfaces to give the retrieved image the appearance of having the new texture data at the selected mapped surface.

Abstract: An image processing method, an image processing device, a training method of a neural network, an image processing method based on a combined neural network model, a constructing method of a combined neural network model, a neural network processor, and a storage medium are provided. The image processing method includes: obtaining, based on an input image, initial feature images of N stages with resolutions from high to low, where N is a positive integer and N>2, performing, based on initial feature images of second to N-th stages, cyclic scaling processing on an initial feature image of a first stage, to obtain an intermediate feature image; and preforming merging processing on the intermediate feature image to obtain an output image. The cyclic scaling processing includes hierarchically-nested scaling processing of N?1 stages, and scaling processing of each stage includes down-sampling processing, concatenating processing, up-sampling processing, and residual link addition processing.

Abstract: Motion contaminated magnetic resonance (MR) images for training an artificial neural network to remove motion artifacts from the MR images are difficult to obtain. Described herein are systems, methods, and instrumentalities for injecting motion artifacts into clean MR images and using the artificially contaminated images for machine learning and neural network training. The motion contaminated MR images may be created based on clean source MR images that are associated with multiple physiological cycles of a scanned object, and by deriving MR data segments for the multiple physiological cycles based on the source MR images. The MR data segments thus derived may be combined to obtain a simulated MR data set, from which one or more target MR images may be generated to exhibit a motion artifact. The motion artifact may be created by manipulating the source MR images and/or controlling the manner in which the MR data set or the target MR images are generated.

Abstract: A fluorescence microscopy method includes a trained deep neural network. At least one 2D fluorescence microscopy image of a sample is input to the trained deep neural network, wherein the input image(s) is appended with a digital propagation matrix (DPM) that represents, pixel-by-pixel, an axial distance of a user-defined or automatically generated surface within the sample from a plane of the input image. The trained deep neural network outputs fluorescence output image(s) of the sample that is digitally propagated or refocused to the user-defined surface or automatically generated. The method and system cross-connects different imaging modalities, permitting 3D propagation of wide-field fluorescence image(s) to match confocal microscopy images at different sample planes. The method may be used to output a time sequence of images (e.g., time-lapse video) of a 2D or 3D surface within a sample.

Abstract: The present disclosure is related to systems and methods for image processing. The method includes obtaining a first image of a first modality. The method includes generating a second image of a second modality by processing, based on a trained machine learning model, the first image. The second modality may be different from the first modality.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media related to video bandwidth optimization, and more particularly, to systems and methods for video resolution downscaling and upscaling a video communications platform. A first video stream comprising first multiple image frames of a first resolution is received. A modified video stream of a second resolution higher than the first resolution, is generated using a trained machine learning network. A user interface may display the modified video stream.

Abstract: A method of visualization, characterization, and detection of objects within an image by applying a local micro-contrast convergence algorithm to a first image to produce a second image that is different from the first image, wherein all like objects converge into similar patterns or colors in the second image.

Abstract: An information processing apparatus and an information processing method capable of accurately recognizing an object to be sensed are provided. One or a plurality of learning models are selected from among learning models corresponding to a plurality of categories, a priority of each of the selected learning models is set, observation data obtained by sequentially compounding pieces of sensor data applied from a sensor is analyzed using the learning model and the priority of the learning model, a setting of sensing at a next cycle is selected based on an analysis result, predetermined control processing is executed in such a manner that the sensor performs sensing at the selected setting of sensing, and the learning model corresponding to the category estimated as the category to which a current object to be sensed belongs with a highest probability is selected based on the categories to each of which the previously recognized object to be sensed belongs.

Abstract: A system, method, and computer program product are disclosed. The method includes receiving a first text unit, extracting features from the first text unit, receiving a second text unit, extracting features from the second text unit, receiving a portion comprising the first text unit and the second text unit, and aggregating the features extracted from the first text unit and the features extracted from the second text unit. The method also includes generating a set of scores for the first text unit, the second text unit, and the portion, and based on the set of scores, selecting at least one ground truth candidate from the first text unit, the second text unit, and the portion. Additionally, the method includes determining that the at least one ground truth candidate includes at least one confirmed ground truth, and adding the at least one confirmed ground truth to a ground truth repository.

Abstract: A load-monitoring system includes a vehicle processor and a camera mounted in a trailer. The vehicle, via the processor, displays a first image of a trailer load, received from a trailer-mounted camera and receives selection of a monitoring point on the image, via a touch-sensitive user interface displaying the image or other selection mechanism. The vehicle also receives selection of a fixed point on the image, via the user interface. If the monitoring point moves more than a threshold amount, relative to the fixed point, for example, in subsequent images captured by the camera, the vehicle alerts the driver.

Abstract: Methods and systems for identifying quantisation parameters for a Deep Neural Network (DNN). The method includes determining an output of a model of the DNN in response to training data, the model of the DNN comprising one or more quantisation blocks configured to transform a set of values input to a layer of the DNN prior to processing the set of values in accordance with the layer, the transformation of the set of values simulating quantisation of the set of values to a fixed point number format defined by one or more quantisation parameters; determining a cost metric of the DNN based on the determined output and a size of the DNN based on the quantisation parameters; back-propagating a derivative of the cost metric to one or more of the quantisation parameters to generate a gradient of the cost metric for each of the one or more quantisation parameters; and adjusting one or more of the quantisation parameters based on the gradients.

Abstract: A method for sparse optical flow based tracking in a computer vision system is provided that includes detecting feature points in a frame captured by a monocular camera in the computer vision system to generate a plurality of detected feature points, generating a binary image indicating locations of the detected feature points with a bit value of one, wherein all other locations in the binary image have a bit value of zero, generating another binary image indicating neighborhoods of currently tracked points, wherein locations of the neighborhoods in the binary image have a bit value of zero and all other locations in the binary image have a bit value of one, and performing a binary AND of the two binary images to generate another binary image, wherein locations in the binary image having a bit value of one indicate new feature points detected in the frame.

Abstract: Given an input image, an image enhancement task, and no external examples available to train on, an Image-Specific Deep Network is constructed tailored to solve the task for this specific image. Since there are no external examples available to train on, the network is trained on examples extracted directly from the input image itself. The current solution solves the problem of Super-Resolution (SR), whereas the framework is more general and is not restricted to SR.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium. In one aspect, a method includes receiving a text prompt describing a scene; processing the text prompt using a text encoder neural network to generate a contextual embedding of the text prompt; and processing the contextual embedding using a sequence of generative neural networks to generate a final video depicting the scene.

Abstract: A computer-implemented method is provided. The computer-implemented method includes inputting a low-resolution image into a generator; and generating a high-resolution image using the generator based on the low-resolution image. Generating the high-resolution image includes processing the low-resolution image through a plurality of super-resolution generating units arranged in series in the generator. A respective output from a respective one of the plurality of super-resolution generating units has a respective increased image resolution as compared to a respective input to the respective one of the plurality of super-resolution generating units.