An image processing apparatus comprises: an acquisition unit for acquiring each of motion vector amounts of video signals each obtained from a plurality of camera units; a determination unit for determining whether or not each of the motion vector amounts is appropriate; and a control unit for performing image blur correction for the video signal for which the motion vector amount determined to be not appropriate has been obtained by using the motion vector amount determined to be appropriate if it is determined by the determination unit that at least one of the motion vector amounts is not appropriate, and to perform image blur correction for the video signals by sharing any one of the motion vector amounts determined to be appropriate by the determination unit or by using the respective motion vector amounts if it is determined by the determination unit that the respective motion vector amounts are appropriate.

Embodiments described herein provide a system for analyzing a gameplay of a first video game. During operation, the system can obtain a stream of video frames associated with the gameplay. The system can then analyze the video frames to identify a set of features of the first video game. Here, a respective feature indicates the characteristics of a virtual object in a virtual environment of the first video game supported by a first game engine. Subsequently, the system can derive, based on the set of identified features, a set of parameters indicating one or more physical characteristics of one or more virtual objects in the virtual environment. The system can store the set of derived parameters in a file format readable by a second game engine different from the first game engine. This allows the second game engine to support a second video game that incorporates the physical characteristics.

Generating a 3D scene reconstruction using depth fusion can include creating a high-resolution sparse depth map by mapping sensor depths from a low-resolution depth map to points corresponding to pixels of a high-resolution color image of a scene. The high-resolution sparse depth map can have the same resolution as the high-resolution color image. A fused sparse depth map can be produced by combining the high-resolution sparse depth map with sparse depths reconstructed from the high-resolution color image. The high-resolution dense depth map can be generated based on fused sparse depths of the fused sparse depth map.

A display apparatus is provided. The display apparatus includes an input interface, a first storage, a display, and a processor. Pixel values corresponding to a predetermined number of lines in an image input through the input interface are stored in the first storage. The processor acquires a first patch of a predetermined size by sampling a number of pixel values located in an outer region of a matrix centering about a specific pixel value from among the pixel values stored in the first storage, acquires a high-frequency component for the specific pixel value based on the acquired first patch, and processes the input image based on the high-frequency component. The display displays the processed image.

An image processing method, including: by a processor: acquiring a fundus image; performing a first enhancement processing on an image of at least a central region of the fundus image, and performing a second enhancement processing, which is different from the first enhancement processing, on an image of at least a peripheral region of the fundus image that is at a periphery of the central region; and generating an enhanced image of the fundus image on the basis of a first image obtained as a result of the first enhancement processing having been performed and a second image obtained as a result of the second enhancement processing having been performed.

An information processing method is executed by a computer and includes: obtaining a third model in which a first model which is a machine learning model that performs a deblurring process of an input image and outputs a feature quantity and a second model which is a machine learning model that performs an object recognition process of the input image and outputs a result of the object recognition are connected so that an output of the first model becomes an input of the second model; training the third model through machine learning so that a difference between a result of object recognition that is output from the third model after a training image with blur is input into the third model and reference data relating to the result of the object recognition corresponding to the training image decreases; and outputting the third model which has undergone the training.

An image processing method includes obtaining a to-be-processed image, performing an image processing operation on the to-be-processed image by inputting the to-be-processed image into a corresponding image processing model to obtain a processed image, and obtaining an output image according to the processed image of the corresponding image processing model. The image processing operation includes at least one of color deviation removal processing or ghost effect removal processing. The image processing model corresponding to the color deviation removal processing is a first image processing model, and the image processing model corresponding to the ghost effect removal processing is a second image processing model.

An array of more than one digital micro-camera, along with the use of patterned illumination and a digital post-processing operation, jointly create a multi-camera patterned illumination (MCPI) microscope. Each micro-camera includes its own unique lens system and detector. The field-over-view of each micro-camera unit at least partially overlaps with the field-of-view of one or more other micro-camera units within the array. The entire field-of-view of a sample of interest is imaged by the entire array of micro-cameras in a single snapshot. In addition, the MCPI system uses patterned optical illumination to improve its effective resolution. The MCPI system captures one or more images as the patterned optical illumination changes its distribution across space and/or angle at the sample. Then, the MCPI system digitally combines the acquired image sequence using a unique post-processing algorithm.

A training method for an image fusion processing model is provided. The method includes: obtaining an image set, and compressing the image set, updating a parameter of an encoder of a single image processing model and a parameter of a decoder of the single image processing model according to a single to-be-replaced face in the original image set, and updating parameters of an encoder and a decoder that are of the image fusion processing model according to different to-be-replaced faces and different target faces that are in the original image set while the parameters of the encoder and the decoder that are of the single image processing model remain unchanged. An image processing method and apparatus for an image fusion processing model, an electronic device, and a storage medium are further provided.

An apparatus and method for reducing the blurriness of tomographic (3D) images constructed from a gamma camera system with one or more VASH (variable-angle slant-hole) collimators. A conventional gamma camera with a VASH collimator exhibits a loss of spatial resolution from the fact that the gamma-ray is entering the detector element at an angle other than normal to the surface. This depth dependence of the spatial localization causes a blurring of the spatial resolution, which is dependent on the incident angle relative to the normal, on the thickness of the detector element and on the stopping length of the gamma-ray in the detector element material. The invention provides an apparatus and method for correcting the spatial location where the gamma ray is recorded to improve the spatial resolution of the system.