Abstract: There are provided a method of knowledge transferring, an information processing apparatus and a storage medium. The method of knowledge transferring includes: obtaining a first model which has been trained in advance with respect to a predetermined task; and training a second model with respect to the predetermined task by utilizing a comprehensive loss function, such that the second model has knowledge of the first model. The comprehensive loss function is based on a first loss function weighted by accuracy of an output result of the first model for a training sample in regard to the predetermined task, and a second loss function. The first loss function represents a difference between processing results of the second model and the first model for the training sample. The second loss function represents accuracy of an output result of the second model for the training sample in regard to the predetermined task.

Abstract: A moiré image processing device is provided, including a light-transmitting film, a light sensor, and an image processor. The light-transmitting film includes a plurality of microlenses, and a light-incident surface and a light-exit surface, where the microlenses are disposed on the light-incident surface, the light-exit surface, or a combination thereof according to a distribution pattern. The light sensor includes a photosensitive surface, where the photosensitive surface faces the light-exit surface, there are a plurality of pixels on the photosensitive surface, and the pixels sense the microlenses to obtain a photosensitive image corresponding to the distribution pattern. The image processor is coupled to the light sensor, where the image processor performs, according to a virtual image and the photosensitive image, image processing of simulating a moiré effect to generate a moiré image, where the virtual image corresponds to the distribution pattern and is similar to the photosensitive image.

Abstract: A method for deblurring a blurred image includes encoding, by at least one processor, a blurred image at a plurality of stages of encoding to obtain an encoded image at each of the plurality of stages; decoding, by the at least one processor, an encoded image obtained from a final stage of the plurality of stages of encoding by using an encoding feedback from each of the plurality of stages and a machine learning (ML) feedback from at least one ML model; and generating, by the at least one processor, a deblurred image in which at least one portion of the blurred image is deblurred based on a result of the decoding.

Abstract: A vehicle position and velocity estimation based on camera and LIDAR data are disclosed.

Abstract: Disclosed is an electronic apparatus. The electronic apparatus includes a processor configured to obtain first upscaling information of an input image using an artificial intelligence (AI) model that is trained to obtain upscaling information of an image. The processor is also configured to downscale the input image based on the obtained first upscaling information, and obtain an output image by upscaling the downscaled image based on an output resolution.

Abstract: Disclosed is an electronic apparatus. The electronic apparatus includes a processor configured to obtain first upscaling information of an input image using an artificial intelligence (AI) model that is trained to obtain upscaling information of an image. The processor is also configured to downscale the input image based on the obtained first upscaling information, and obtain an output image by upscaling the downscaled image based on an output resolution.

Abstract: Embodiments are directed towards hue-based video enhancement. An example method includes processing low dynamic range (LDR) video content to generate an inverse tone map (ITM) for transforming the LDR video content to high dynamic range (HDR) video content, converting the LDR video content into Hue, Saturation and Lightness (HSY) color space to produce H-channel data, S-channel data, and Y-channel data, de-noising the H-channel data, remapping the de-noised H-channel data, the S-channel data, and the Y-channel data based on the ITM; and rendering the HDR video content based thereon.

Abstract: Embodiments described herein provide a system for generating semantically accurate synthetic images. During operation, the system generates a first synthetic image using a first artificial intelligence (AI) model and presents the first synthetic image in a user interface. The user interface allows a user to identify image units of the first synthetic image that are semantically irregular. The system then obtains semantic information for the semantically irregular image units from the user via the user interface and generates a second synthetic image using a second AI model based on the semantic information. The second synthetic image can be an improved image compared to the first synthetic image.

Abstract: A computer-implemented method includes applying a filter to input data based on an initial set of parameters to generate an initial feature map. The filter is configured to activate a filter function that involves a periodic function. The method includes performing a first linear transform on the initial feature map based on a subset of a first set of parameters to generate a first linear transform. The method includes applying the filter to the input data based on another subset of the first set of parameters to generate a first feature map. The method includes performing a multiplicative operation on the first linear transform and the first feature map to generate a first product. The method includes performing a second linear transform on the first product based on a subset of a second set of parameters to generate a second linear transform. The method includes generating output data that takes into account at least the second linear transform.

Abstract: Images of a hand may be used to identify users. Quality, detail, and so forth of these images may vary. An image is processed to determine a first spatial mask. A first neural network comprising many layers uses the first spatial mask at a first layer and a second spatial mask at a second layer to process images and produce an embedding vector representative of features in the image. The first spatial mask provides information about particular portions of the input image, and is determined by processing the image with an algorithm such as an orientation certainty level (OCL) algorithm. The second spatial mask is determined using unsupervised training and represents weights of particular portions of the input image as represented at the second layer. The use of the masks allows the first neural network to learn to use or disregard particular portions of the image, improving overall accuracy.

Abstract: Techniques are generally described for predicting text relevant to image data. In various examples, the techniques may include receiving image data comprising a first portion. The first portion of the image data may correspond to a first plurality of pixels when rendered on the display. Text data comprising a first text related to the first portion of the image data may be received. A first vector representation of the first portion of the image data may be determined. In some examples, a correspondence between the first portion of the image data and the first text may be determined based at least in part on the first vector representation. A first identifier of the first portion of image data may be stored in a data structure in association with a second identifier of the first text.

Abstract: An apparatus includes a memory and a processing circuit. The memory may be configured to store image data of an image. The processor circuit may be configured to (a) copy the image data of the image from the memory to a first memory buffer of the processor circuit, (b) calculate first vector values for each pixel location in the image using the image data stored in the first memory buffer, (c) calculate second vector values for each pixel location in the image using the image data stored in the first memory buffer and the first vector values, (d) transform the image data stored in the first memory buffer by adding the second vector values to corresponding image data, (e) storing the transformed image data to the memory, and (f) repeating steps (a) through (e) until the image data of the image has been transformed.

Abstract: A method and device are provided for inpainting image. An electronic device can be used for: determining an inpainting region of the image, wherein the inpainting region includes a defective region; obtaining original texture information of the inpainting region; determining inpainting pixel blocks and backup pixel blocks, wherein the inpainting pixel blocks include inpainting pixels and first type pixels; inpainting all inpainting pixels of the inpainting pixel blocks based on the backup pixel blocks; and superimposing the original texture information in the inpainting region.

Abstract: Aspects of the present disclosure relate to a computer-implemented method of processing data portion. The method comprises processing a first data portion in a convolutional neural network to generate a first input to an activation function in the convolutional neural network; providing a first output by applying the activation function to the first input; and storing an indicator, representative of the first input to the activation function, for the first data portion. The method further comprises determining whether to provide a second output by applying the activation function to a second input, generated from a second data portion, based at least in part on an evaluation of the indicator for the first data portion.

Abstract: A vehicle having one or more cameras, configured to record one or more images of a person approaching the vehicle. The camera(s) can be configured to send biometric data derived from the image(s). The vehicle can include a computing system configured to receive the biometric data and to determine a risk score of the person based on the received biometric data and an AI technique, such as an ANN or a decision tree. The received biometric data or a derivative thereof can be input for the AI technique. The computing system can also be configured to determine whether to notify a driver of the vehicle of the risk score based on the risk score exceeding a risk threshold. The vehicle can also include a user interface, configured to output the risk score to notify the driver when the computing system determines the risk score exceeds the risk threshold.

Abstract: Anti-spoofing of a deep learning neural network may include receiving, by an artificial neural network implemented in hardware, an image and multi-dimensional spatial frequency data for the image. The artificial neural network is trained using training images and multi-dimensional spatial frequency data for the training images. Using the artificial neural network, a classification for an object in an image is determined based on the image and the multi-dimensional spatial frequency data for the image.

Abstract: The exemplary embodiments relate to converting standard dynamic range (SDR) content to high dynamic range (HDR) content. An SDR image may be decomposed into a base layer of the SDR image that includes low frequency information from the SDR image and a detail layer of the SDR image that includes high frequency information from the SDR image. A base layer of an HDR image may be generated using the base layer of the SDR image and a detail layer of the HDR image may be generated using the detail layer of the SDR image. An HDR image is then generated using the base layer of the HDR image and the detail layer of the HDR image.

Abstract: A method of analyzing cell populations includes receiving, by a transceiver of a computing device, an image of a tissue sample. The method also includes analyzing, by a processor of the computing device, the image of the tissue sample using image analysis. The image analysis parameters are determined by machine learning. The method also includes determining, by the processor and based on the analyzing, one or more cell features, such as shape, of a cell in the tissue sample. The method further includes identifying, by the processor, an interaction of the cell with an additional cell based at least in part on the shape of the cell.

Abstract: A neural network system for detecting at least one object in at least one image, the system includes a plurality of object detectors. Each object detector receives respective image information thereto. Each object detector includes a respective neural network. Each the neural network including a plurality of layers. Layers in different object detectors are common layers when the layers receive the same input thereto and produce the same output therefrom. Common layers are computed only once during object detection for all the different object detectors.

Abstract: For registration of medical images with deep learning, a neural network is designed to include a diffeomorphic layer in the architecture. The network may be trained using supervised or unsupervised approaches. By enforcing the diffeomorphic characteristic in the architecture of the network, the training of the network and application of the learned network may provide for more regularized and realistic registration.