A multi-task deep learning-based real-time matting method for non-green-screen portraits is provided. The method includes: performing binary classification adjustment on an original dataset, inputting an image or video containing portrait information, and performing preprocessing; constructing a deep learning network for person detection, extracting image features by using a deep residual neural network, and obtaining a region of interest (ROI) of portrait foreground and a portrait trimap in the ROI through logistic regression; and constructing a portrait alpha mask matting deep learning network. An encoder sharing mechanism effectively accelerates a computing process of the network. An alpha mask prediction result of the portrait foreground is output in an end-to-end manner to implement portrait matting. In this method, green screens are not required during portrait matting. In addition, during the matting, only original images or videos need to be provided, without a need to provide manually annotated portrait trimaps.

Embodiments of the present application provide a method and a device of inverse tone mapping and an electronic device. The method includes: obtaining one or more low dynamic range images; performing a decomposition operation to the low dynamic range image to acquire a detail layer and a basic layer of the low dynamic range image; restoring the detail layer and the basic layer by using a predetermined first restoration network and a second restoration network to acquire restored detail layer and basic layer; and adjusting the restored detail layer and basic layer by using a predetermined fusion network to acquire an adjusted high dynamic range image. With the technical solution of the present application, the conversion from a low dynamic range image to a high dynamic range image can be more robustly completed without complicated parameter settings.

A method for automated detection of landmarks from 3D medical image data using deep learning according to the present inventive concept, the method includes receiving a 3D volume medical image, generating a 2D intensity value projection image based on the 3D volume medical image, automatically detecting an initial anatomical landmark using a first convolutional neural network based on the 2D intensity value projection image, generating a 3D volume area of interest based on the initial anatomical landmark and automatically detecting a detailed anatomical landmark using a second convolutional neural network different from the first convolutional neural network based on the 3D volume area of interest.

A method the following operations: downscaling an input image to generate a scaled image; performing, to the scaled image, a first convolutional neural networks (CNN) modeling process with first non-local operations, to generate global parameters; and performing, to the input image, a second CNN modeling process with second non-local operations that are performed with the global parameters, to generate an output image corresponding to the input image. A system is also disclosed herein.

A processing method for enhancing the image quality of an image, more particularly a digital medical grey scale image, that comprises the steps of a) decomposing an original image into multiple detail images at different resolution levels and/or orientations, b) processing the detail images to obtain processed detail images, c) computing a result image by applying a reconstruction algorithm to the processed detail ages, said reconstruction algorithm being such that if it were applied to the detail images without processing, then said original image or a close approximation thereof would be obtained, the processing of the detail images comprises the steps of: d) calculating at least one conjugate detail image, and e) computing at least one value of the processed detail images as a function of said conjugate detail image and said detail images.

Provided are an image enhancement method and apparatus, an electronic device, and a storage medium. The image enhancement method includes: acquiring an original image, and configuring the original image as a current image; selecting a renderer from a plurality of pre-trained renderers as a current renderer in response to the current image satisfying a preset enhancement condition; and inputting the current image to the current renderer, and outputting, through the current renderer, an enhanced image of the current image in a dimension corresponding to the current renderer; and repeating the preceding operation by configuring the enhanced image of the current image in the dimension corresponding to the current renderer as the current image until the current image does not satisfy the enhancement condition.

In variants, the method can include: detecting a property within a set of measurements; determining a set of property parameters based on the detection; determining a set of higher-resolution measurements based on the set of property parameters; and determining a set of property attributes based on the set of higher-resolution measurements.

An image processing method and a device configured to implement the same are disclosed. The method comprises: obtaining optical input from a hybrid imaging device, wherein an obtained optical input comprises a first component and a second component that temporally corresponds to the first component; wherein the first component of the obtained optical input corresponds to a first temporal resolution, while the second component of the obtained optical input corresponds to a second temporal resolution higher than that of the first component; performing image restoration operation on a first subset of the first component of the obtained optical input in accordance with data from the second component of the obtained optical input; and performing image fusion operation to generate fused image data from an output of the image restoration operation and a second subset of the first component of the obtained optical input.

A computer system is provided comprising a classification model management server computer configured, by instructions, to: receive a new image from a user device; apply a first digital model to first regions within the new image for classifying each of the first regions into a particular class; apply a second digital model to second regions within the new image for classifying each of the second regions into a particular class; and transmit classification data related to the class of the first regions and the class of the second regions to the user device. In connection therewith, the second regions each generally correspond to a combination of multiple first regions.

A system and method for virtual camera configuration and selection. For example, one embodiment of a system comprises: a decode subsystem comprising circuitry to concurrently decode a plurality of video streams captured by cameras at an event to generate decoded video streams from a perspective of corresponding virtual cameras (VCAMs); video evaluation logic to apply at least one video quality metric to determine a quality value for the decoded video streams or a subset thereof, and to rank the decoded video streams based, at least in part, on the quality values associated with the decoded video streams; preview logic to provide the decoded video streams or modified versions thereof to one or more computing devices accessible to one or more video production team members and to further provide the quality values and/or the rank generated by the video quality evaluation logic; stream selection hardware logic to select a subset of the plurality of decoded video streams based on input from the one or more video production team members; and transcoder hardware logic to transcode the subset of the plurality of decoded video streams for live transmission over a public or private network.