A device includes a memory and one or more processors. The memory is configured to store instructions. The one or more processors are configured to execute the instructions to apply a neural network to a first image to generate an enhanced image. The one or more processors are also configured to execute the instructions to adjust at least a portion of a high-frequency component of the enhanced image based on a motion compensation operation to generate an adjusted high-frequency image component. The one or more processors are further configured to execute the instructions to combine a low-frequency component of the enhanced image and the adjusted high-frequency image component to generate an adjusted enhanced image.

A device includes a memory and one or more processors. The memory is configured to store an image enhancement network of an image enhancer. The one or more processors are configured to predict an image compression quality of an image of a stream of images. The one or more processors are also configured to configure the image enhancer based on the image compression quality. The one or more processors are further configured to process, using the image enhancement network of the configured image enhancer, the image to generate an enhanced image.

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.

Embodiments of the present disclosure provide a method, an electronic device, and a program product for image processing. In one embodiment, a method may include: at an edge node of a network, obtaining a first image generated based on data associated with a target event, wherein the first image has a first resolution ratio. Additionally, the method may further include: sending a second image converted from the first image to a terminal device, wherein the second image has a second resolution ratio higher than the first resolution ratio. According to the embodiments of the present disclosure, by rendering a low-resolution-ratio image at a cloud server and transmitting the image to an edge node or a terminal device for reconstructing a high-resolution-ratio image, the bandwidth and time delay of high-definition image transmission can be significantly reduced, so that the user experience is improved.

An imaging device, according to one embodiment of the present invention, comprises: an input unit for receiving first Bayer data having a first resolution and a noise level; and a convolutional neural network for outputting second Bayer data having a second resolution by using the noise level and the first Bayer data.

Provided are a depth completion method and apparatus using spatial-temporal information. The depth completion apparatus according to the present invention comprises a processor; and a memory connected to the processor, wherein the memory stores program instructions executable by the processor for performing operations comprising receiving an RGB image and a sparse image through a camera and LiDAR, generating a dense first depth map by processing color information of the RGB image through a first branch based on an encoder-decoder, generating a dense second depth map by up-sampling the sparse image through a second branch based on an encoder-decoder, generating a third depth map by fusing the first depth map and the second depth map, and generating a final depth map including a trajectory of a moving object included in an RGB image continuously captured during movement by inputting the third depth map to a convolution long term short memory (LSTM).

Examples of methods are described. In some examples, a method includes generating, using a first branch of a machine learning model, a first agent map based on a layer image. In some examples, the method includes generating, using a second branch of the machine learning model, a second agent map. In some examples, the first agent map and the second agent map indicate printing locations for different agents.

In various embodiments, a training application trains a machine learning model to preprocess images. In operation, the training application computes a chroma sampling factor based on a downscaling factor and a chroma subsampling ratio. The training application executes a machine learning model that is associated with the chroma sampling factor on data that corresponds to both an image and a first chroma component to generate preprocessed data corresponding to the first chroma component. Based on the preprocessed data, the training application updates at least one parameter of the machine learning model to generate a trained machine learning model that is associated with the first chroma component.

An image processing method and a device, where the image processing method is performed by a terminal having a digital zoom function, and the method includes determining a target zoom magnification based on a selection input of a user, collecting a to-be-processed image, and processing the to-be-processed image using a target super-resolution convolutional neural network model to obtain a processed image corresponding to the target zoom magnification, where the target super-resolution convolutional neural network model is obtained by training a super-resolution convolutional neural network model using a high-definition training image, a low-definition training image, and a mask image.

A method for image capture includes identifying a bright spot in an image. A neural network is used to recover details in bright spot area through a trained de-noising process. Post-processing of the image is conducted to match image parameters of recovered details in the bright spot area to another area of the image.