Abstract: A filter process is performed on point cloud data using a representative value of the point cloud data for each local region obtained by dividing a three-dimensional space. A two-dimensional plane image on which the point cloud data subjected to the filter process is projected is encoded, and a bitstream is generated. The filter process can be performed by, for example, an information processing apparatus, an image processing apparatus, electronic equipment, an information processing method, a program, or the like.

Abstract: An apparatus to facilitate video motion smoothing is disclosed. The apparatus comprises one or more processors including a graphics processor, the one or more processors including circuitry configured to receive a video stream, decode the video stream to generate a motion vector map and a plurality of video image frames, analyze the motion vector map to detect a plurality of candidate frames, wherein the plurality of candidate frames comprise a period of discontinuous motion in the plurality of video image frames and the plurality of candidate frames are determined based on a classification generated via a convolutional neural network (CNN), generate, via a generative adversarial network (GAN), one or more synthetic frames based on the plurality of candidate frames, insert the one or more synthetic frames between the plurality of candidate frames to generate up-sampled video frames and transmit the up-sampled video frames for display.

Abstract: A sensor device is described herein. The sensor device includes a multi-dimensional optical sensor and processing circuitry, wherein the multi-dimensional optical sensor generates images and the processing circuitry is configured to output data that is indicative of hemodynamics of a user based upon the images. The sensor device is non-invasive, and is able to be incorporated into wearable devices, thereby allowing for continuous output of the data that is indicative of the hemodynamics of the user.

Abstract: A computer-implemented method for facilitating opportunistic screening for cardiomegaly includes obtaining a set of computed tomography (CT) images. The set of CT images captures at least a portion of a heart of a patient, and the set of CT images is captured for a purpose independent of assessing cardiomegaly. The method further includes using the set of CT images as an input to an artificial intelligence (AI) module configured to determine a heart measurement based on CT image set input. The method also includes obtaining heart measurement output generated by the AI module and, based on the heart measurement output, classifying the patient into one of a plurality of risk levels for cardiomegaly. The classification is operable to trigger additional action based on the corresponding risk level for the patient.

Abstract: A target-oriented reinforcement learning method according to an embodiment includes: collecting data related to the target of reinforcement learning as target data in the process of performing the reinforcement learning; learning the collected target data as auxiliary learning for the reinforcement learning; and incorporating the results of the learning of the target data into the performance of the reinforcement learning.

Abstract: The present invention discloses a denoising model of Monte Carlo rendering based on a Generative Adversarial Network (GAN) and its construction method, including: constructing a training sample and constructing a Generative Adversarial Network (GAN), including Denoising Net and Critic Net, wherein Denoising Net is used to denoise the input noise rendering image and auxiliary features, and output the denoising rendering image, and Critic Net is used to classify the input denoising rendering image and the target rendering image corresponding to the noise rendering image, and output the classification result. The training samples are used to tune the network parameters of the Generative Adversarial Network (GAN). After the tuning is completed, the denoising network determined by the network parameters is used as the Monte Carlo rendering image denoising model. A denoising method and device for the Monte Carlo rendering image are also disclosed, which can realize the denoising of noisy Monte Carlo renderings.

Abstract: A display defect detection system and a detection method thereof are disclosed. A display defect detection system includes a preprocessing circuit receiving a capture image of a test pattern, displayed by a display panel, as a panel image including diagonal Mura and preprocessing the panel image to output a preprocessing image and a Mura detection circuit calculating a final feature value of the diagonal Mura by multiplying a first feature value, in which a luminance difference of the diagonal Mura is reflected, by a second feature value in which a shape ratio of the diagonal Mura is reflected, on the basis of an edge map of the preprocessing image, and detecting a display position of the diagonal Mura on the basis of the final feature value of the diagonal Mura.

Abstract: A method with object detection includes obtaining a first point cloud feature based on point cloud data of an image and determining at least one object in the image based on the first point cloud feature.

Abstract: The disclosure relates to a method for correcting a movement of an object occurring during an MR image acquisition. The method includes: determining a motion model describing possible movements of the object based on a defined number of degrees of freedom; detecting a motion of a marker provided on the object with a motion sensor; determining a description of the motion model in a common coordinate system; determining the motion of the marker in the common coordinate system; determining a first motion of the object in the common coordinate system using the description of the motion model, the first motion being the motion that best matches the determined motion of the marker in the common coordinate system using the defined number of degrees of freedom; and correcting the movement of the object based on the determined first motion in order to determine at least one motion corrected MR image.

Abstract: Systems, and method and computer readable media that store instructions for.

Abstract: Provided is a method of providing an interpretation result using visual information, and the method includes: acquiring a spatial domain image including line-of-sight information of a user and gaze position information in the spatial domain image; segmenting the acquired spatial domain image into a plurality of images; detecting text areas including text for each of the segmented images; generating text blocks, each of which is a text recognition result for each of the detected text areas, and determining the text block corresponding to the gaze position information; converting a first language included in the determined text block into a second language that is a target language; and providing the user with a conversion result of the second language.

Abstract: Example implementations include a method, apparatus and computer-readable medium of computer vision configured for person classification, comprising receiving, during a first period of time, a plurality of image frames of an environment, identifying images of persons from each frame of the plurality of image frames, and determining a respective vector representation of each of the images. The implementations include generating a probability distribution indicative of a likelihood of a particular vector representation appearing in the plurality of image frames and identifying an associate vector representation by sampling the probability distribution using a probability model. The implementations include determining an input vector representation of an input image identified in an image frame depicting a person and received during a second period of time.

Abstract: The present disclosure provides an image processing circuit including a neural network processor, a background processing circuit and a blending circuit. The neural network processor is configured to process input image data to determine whether the input image data has a predetermined object so as to generate to heat map. The background processing circuit blurs the input image data to generate blurred image data. The blending circuit blends the input image data and the blurred image data according to the heat map to generate output image data.

Abstract: A method for training a super-resolution network may include obtaining a low resolution image; generating, using a first machine learning model, a first high resolution image based on the low resolution image; generating, using a second machine learning model, a second high resolution image based on the first high resolution image and an unpaired dataset of high resolution images; obtaining a training data set using the low resolution image and the second high resolution image; and training the super-resolution network using the training data set.

Abstract: The information processing includes: an acquisition unit for acquiring an image including a face image of a person; and a selection unit for selecting the image in which the part other than the face of a target person is captured among the plurality of images by using the position of the face image of a person other than the target person in the acquired image.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately, efficiently, and flexibly generating modified digital images utilizing a guided inpainting approach that implements a patch match model informed by a deep visual guide. In particular, the disclosed systems can utilize a visual guide algorithm to automatically generate guidance maps to help identify replacement pixels for inpainting regions of digital images utilizing a patch match model. For example, the disclosed systems can generate guidance maps in the form of structure maps, depth maps, or segmentation maps that respectively indicate the structure, depth, or segmentation of different portions of digital images. Additionally, the disclosed systems can implement a patch match model to identify replacement pixels for filling regions of digital images according to the structure, depth, and/or segmentation of the digital images.

Abstract: An image synthesis device according to a disclosed embodiment is an image synthesis device has one or more processors and a memory which stores one or more programs executed by the one or more processors. The image synthesis device includes a first artificial neural network model provided to learn each of a first task of using a damaged image as an input to output a restored image and a second task of using an original image as an input to output a reconstructed image, and a second artificial neural network model trained to use the reconstructed image output from the first artificial neural network model as an input and improve the image quality of the reconstructed image.

Abstract: An image processing apparatus processes a color filter mosaic, CFM, image of a scene into a final image of the scene. The image processing apparatus includes processing circuitry configured to implement a neural network. The neural network is configured to process the CFM image into an enhanced CFM image. The processing circuitry is further configured to transform the enhanced CFM image into the final image.

Abstract: As provided herein, a domain model, corresponding to a domain of an image, may be merged with a pre-trained fundamental model to generate a trained fundamental model. The trained fundamental model may comprise a feature description of the image converted into a binary code. Responsive to a user submitting a search query, a coarse image search may be performed, using a search query binary code derived from the search query, to identify a candidate group, comprising one or more images, having binary codes corresponding to the search query binary code. A fine image search may be performed on the candidate group utilizing a search query feature description derived from the search query. The fine image search may be used to rank images within the candidate group based upon a similarity between the search query feature description and feature descriptions of the one or more images within the candidate group.

Abstract: A video quality improvement method may comprise: inputting a structure feature map converted from current target frame by first convolution layer to first multi-task unit and second multi-task unit, which is connected to an output side of first multi-task unit, among the plurality of multi-task units; inputting a main input obtained by adding the structure feature map to a feature space, which is converted by second convolution layer from those obtained by concatenating, in channel dimension, a previous target frame and a correction frame of the previous frame to first multi-task unit; and inputting current target frame to Nth multi-task unit connected to an end of output side of second multi-task unit, wherein Nth multi-task unit outputs a correction frame of current target frame, and machine learning of the video quality improvement model is performed using an objective function calculated through the correction frame of current target frame.