Abstract: Methods and systems are provided for transforming sketches into stylized electronic paintings. A neural network system is trained where the training includes training a first neural network that converts input sketches into output images and training a second neural network that converts images into output paintings. Similarity for the first neural network is evaluated between the output image and a reference image and similarity for the second neural network is evaluated between the output painting, the output image, and a reference painting. The neural network system is modified based on the evaluated similarity. The trained neural network is used to generate an output painting from an input sketch where the output painting maintains features from the input sketch utilizing an extrapolated intermediate image and reflects a designated style from the reference painting.

Abstract: The present disclosure provides a material identification method and a device based on laser speckle and modal fusion, an electronic device and a non-transitory computer readable storage medium. The method includes: performing data acquisition on an object by using a structured light camera to obtain a color modal image, a depth modal image and an infrared modal image; preprocessing the color modal image, the depth modal image and the infrared modal image; and inputting the color modal image, the depth modal image and the infrared modal image preprocessed into a preset depth neural network for training, to learn a material characteristic from a speckle structure and a coupling relation between color modal and depth modal, to generate a material classification model for classifying materials, and to generate a material prediction result in testing by the material classification model of the object.

Abstract: Disclosed herein is a color restoration method and apparatus. The color restoration method may include pre-processing an input image, determining whether color is distorted, and restoring the color of the input image in an RGB scale or a grayscale according to whether the color is distorted. According to the present disclosure, color of a low light image may be restored using a deep neural network model trained through deep learning of a 5G network and color restoration.

Abstract: Disclosed are a method and an apparatus for image encoding/decoding that support a plurality of layers. The method for image decoding that supports a plurality of layers includes decoding information of a first layer which a picture of a second layer including a current decoding target block refers to; mapping the information of the first layer to a picture size of the second layer, configuring a reference picture list for the picture of the second layer by adding the mapped information of the first layer and generating prediction samples of the current decoding target block by predicting the current decoding target block of the second layer based on the reference picture list, and the information of the first layer includes at least one of a sample value and motion information of the first layer picture.

Abstract: A computer implemented method for recognizing a hand gesture using a random forest model includes training the random forest model. The method also includes obtaining image data. The method further includes clustering a plurality of pixels from the image data to generate a plurality of clusters. Moreover, the method includes analyzing the plurality of clusters using a rejection cascade to generate a plurality of selected candidates. In addition, the method includes analyzing the plurality of selected candidates using a classification decision tree from the random forest model. The method also includes skeletonizing the plurality of selected candidates to generate a one dimension plus branches hand model. The method further includes analyzing the one dimension plus branches hand model using a regression decision tree from the random forest model.

Abstract: An image processing method is provided, including: obtaining image data of a cavity wall of an organ; unfolding the cavity wall; and generating an image of the unfolded cavity wall. The unfolding of the cavity wall may include: obtaining a mask and a centerline of the organ; obtaining a connected region of the mask; dividing the connected region into at least one equidistant block; determining an orientation of the equidistant block in a three-dimensional coordinate system including a first direction, a second direction and a third direction; determining an initial normal vector and an initial tangent vector of a center point of the centerline; assigning a projection of the initial normal vector to a normal vector of a light direction of the center point; assigning the third direction or an reverse direction of the third direction to a tangent vector of the light direction of the center point.

Abstract: Embodiments of the present systems and methods may provide imaging techniques for multidirectional imaging, light conditioning, illumination sequences, or machine learning to create algorithms created from training by other advanced imaging techniques. In an embodiment, a method for generating an image may comprise obtaining an image of an object produced by a camera and generating, from the obtained image produced by a conventional camera, using an artificial intelligence model and imaging process, an output image including additional information similar to additional information present in an image of the object produced by an advanced imaging system.

Abstract: Disclosed is a method for annotation based on deep learning, which is performed by a computing device. The method may include: performing first learning of an agent model as supervised learning based on a first bounding box of an interest object corresponding to a ground truth (GT) for annotation; and performing second learning of the agent model as reinforcement learning based on a second bounding box of the interest object randomly sampled according to a constraint for geometric transform of a bounding box.

Abstract: Systems and methods for distributing photo filters based on the location of the object in the image are described. A photo filter publication system detects that a client device in communication with the system has captured an image, identifies an object in the image, identifies a location of the object in the image, identifies an image overlay associated with the identified location and having object criteria satisfied by the identified object, and provides the identified image overlay to the client device.

Abstract: A detection apparatus to extract features from an image; determine the number of candidate regions of the object in the image based on the extracted features, wherein the determined number of the candidate regions is decided by a position and shape of the candidate regions; and to detect the object from the image based on at least the extracted features and the determined number, position and shape of the candidate regions.

Abstract: A method includes capturing a first image associated with a portion of a display screen being shared. The method further includes rendering the first image in a preview window of the display screen being shared to form a second image. The second image is captured so as to determine whether the first image is duplicated in the second image. The duplication of the first image in the second image is masked to form a third image. The third image is rendered in the preview window.

Abstract: Disclosed herein is an image deep learning model training method. The method includes sampling a twin negative comprising a first negative sample and a second negative sample by selecting the first negative sample with a highest similarity out of an anchor sample and a positive sample constituting a matching pair in each class and by selecting the second negative sample with a highest similarity to the first negative sample, and training the samples to minimize a loss of a loss function in each class by utilizing the anchor sample, the positive sample, the first and second negative samples for each class. The first negative sample is selected in a different class from a class comprising the matching pair, and the second negative sample is selected in a different class from classes comprising the matching pair and the first negative sample.

Abstract: A pose determination method for a subject includes identifying a plurality of candidate regions from depth data representing an environment based on a depth connectivity criterion, determining a first region including a first subset of the plurality of candidate regions based on an estimation regarding a first pose component of the subject, determining a second region including a second subset of the plurality of candidate regions that are disconnected from the first subset of the plurality of candidate regions based on relative locations of the first region and the second region, generating a collective region by associating the first region with the second region, identifying the first pose component and a second pose component of the subject from the collective region, determining a spatial relationship between the first pose component and the second pose component, and generating a controlling command based on the spatial relationship.

Abstract: A method is presented. The method includes determining a number of landmarks in an image comprising multiple pixels. The method also includes determining a number of channels for the image based on a function of the number of landmarks. The method further includes determining, for each one of the number of channels, a confidence of each pixel of the multiple pixels corresponding to a landmark. The method still further includes identifying the landmark in the image based on the confidence.

Abstract: Camera or object pose calculation is described, for example, to relocalize a mobile camera (such as on a smart phone) in a known environment or to compute the pose of an object moving relative to a fixed camera. The pose information is useful for robotics, augmented reality, navigation and other applications. In various embodiments where camera pose is calculated, a trained machine learning system associates image elements from an image of a scene, with points in the scene's 3D world coordinate frame. In examples where the camera is fixed and the pose of an object is to be calculated, the trained machine learning system associates image elements from an image of the object with points in an object coordinate frame. In examples, the image elements may be noisy and incomplete and a pose inference engine calculates an accurate estimate of the pose.

Abstract: In a color printing environment, functions for printing color management are dissociated. An abstraction layer is also provided to facilitate setting and evaluation of all factors relating to color print and prediction.

Abstract: A surroundings monitoring system for a work machine includes a memory and a processor coupled to the memory. The processor is configured to detect an obstacle present around the work machine and control an output apparatus mounted on the work machine. The processor is configured to display an output image on a display apparatus. The output image includes an image part generated using a captured image of an image capturing apparatus attached to the work machine and an icon of the work machine. The processor is configured to highlight, among image parts around the icon, an image part corresponding to a direction in which or a position at which the detected obstacle is present.

Abstract: A method, apparatus, and system for generating tight two-dimensional (2D) bounding boxes for visible objects in a three-dimensional (3D) scene is disclosed. A two-dimensional (2D) segmentation image of a three-dimensional (3D) scene comprising one or more objects is generated by rendering the 3D scene with a segmentation camera. Each of the objects is rendered in a single respective different color. Next, one or more visible objects in the 3D scene are identified among the one or more objects based on the segmentation image. Next, a 2D amodal segmentation image for each of the visible objects in the 3D scene is generated separately. Each amodal segmentation image comprises only the single visible object for which it is generated. Thereafter, a 2D bounding box is generated for each of the visible objects in the 3D scene based on the amodal segmentation image for the visible object.

Abstract: A method includes: acquiring data including moving image obtained by photographing a target and annotation images each indicative of a region of the target in each of frame images in the moving image; executing a process using the data. The process includes: detecting the target in the frame images; inputting, to an auto-encoder, an image obtained by combining partial images including the target and peripheral region images of the target detected in a given number of preceding and succeeding second frame images in a time series of the moving image of a first frame image; inputting a partial image corresponding to the first frame image to a neural network performing a segmentation; updating parameter of the auto-encoder and the neural network based on a difference between an image obtained by combining images from the auto-encoder and the neural network and a partial image of the annotation image.

Abstract: There is provided a computer implemented method of measuring a temperature of a subject, comprising: receiving a sequence of a plurality of thermal images of a subject captured by a thermal sensor, analyzing the sequence of the plurality of thermal images to identify at least one target thermal image depicting an upper region of a tongue of the subject, analyzing the at least one target thermal image to identify an estimated temperature of the upper region of the tongue, and providing the estimated temperature of the upper region of the tongue.