The present disclosure relates to an image merging system that automatically and seamlessly detects and merges missing people for a set of digital images into a composite group photo. For instance, the image merging system utilizes a number of models and operations to automatically analyze multiple digital images to identify a missing person from a base image, segment the missing person from the second image, and generate a composite group photo by merging the segmented image of the missing person into the base image. In this manner, the image merging system automatically creates merged group photos that appear natural and realistic.

A computer-implemented method for modifying X-ray projection images of a subject region includes: generating a set of combined two-dimensional (2D) projections of a subject region, wherein each combined 2D projection includes one or more mask-bordering pixels and one or more mask-edge pixels; forming a three-dimensional (3D) matrix of the set of combined 2D projections; based on the 3D matrix, generating a linear algebraic system for determining pixel values for pixels indicated in a set of 2D projection metal masks, wherein a first change in slope of pixel value associated with a mask-edge pixel of a combined 2D projection is constrained to equal a second change in slope of pixel value associated with a mask-bordering pixel of a combined 2D projection; determining values for a variable vector of the linear algebraic system; and generating a set of inpainted 2D projections by modifying initial 2D projections with values for the variable vector.

An information processing device includes one or more memories and one or more processors. The one or more processors and the one or more memories are configured to receive control information and data that contains three-dimensional position information generated by a three-dimensional range sensor and convert, based on the received control information, the three-dimensional position information contained in the data received from the three-dimensional range sensor into two-dimensional image data containing information on a distance from a predetermined viewpoint.

A non-transitory computer readable medium storing data and computer implementable instructions that, when executed by at least one processor, cause the at least one processor to perform operations for generating cross section views of a wound, the operations including receiving 3D information of a wound based on information captured using an image sensor associated with an image plane substantially parallel to the wound; generating a cross section view of the wound by analyzing the 3D information; and providing data configured to cause a presentation of the generated cross section view of the wound.

One embodiment provides a method comprising receiving an input video comprising low-resolution (LR) frames and corresponding super-resolution (SR) frames, and generating a motion-compensated previous SR frame based on a current LR frame of the video and a motion-compensated previous residual frame of the video. The previous SR frame aligns with a current SR frame corresponding to the current LR frame. The method further comprises, in response to determining there is a mismatch between the previous SR frame and the current SR frame, correcting in the current SR frame errors that result from motion compensation based on the motion-compensated previous SR frame. The method further comprises restoring details to the current SR frame that were lost as a result of the correcting, and suppressing flickers of the current SR frame on the frequency domain, resulting in a flicker-suppressed current SR frame for presentation on a display.

A method, apparatus, and a non-transitory computer-readable storage medium for sub-band image reconstruction. The method may include obtaining an image captured by a camera. The method may also obtain a transform image based on the image captured by the camera. The transform image may be in a transform domain. The method may further obtain decomposed image components of the transform image. The decomposed image components may include a low frequency component and at least one high frequency component. The method may also obtain a reconstructed image based on at least two neural networks processing the decomposed image components in the transform domain

Devices, methods, and computer readable media to provide enhanced images in multi-camera systems, e.g., by using images captured by cameras with different optical properties and/or sensors. In one embodiment, the techniques comprise reference-based image super-resolution techniques for producing, with a first neural network employing robust feature aggregation techniques (e.g., techniques able to blend between single-image enhancement and feature aggregation, when appropriate), an enhanced output image that attempts to match the quality characteristics of each of region in a lower quality (e.g., shorter focal length, larger field of view (FOV)) input image with the quality characteristics of the region's determined guidance region from at least a second, i.e., higher quality (e.g., longer focal length, smaller FOV image) input image. The guidance regions from the higher quality image that are determined for each region from the lower quality input image may be determined by performing homographic mapping and/or semantic feature matching techniques.

An image processing system includes an image acquisition unit configured to acquire an image signal generated by an imaging device that captures an optical image having a low-distortion region and a high-distortion region, a setting unit configured to set a distortion-correction region on which distortion-correction is performed for the image signal and a non-distortion-correction region on which distortion-correction is not performed for the image signal on the basis of characteristics of the optical image; and a display signal generation unit configured to perform distortion-correction for the image signal of the distortion-correction region on the basis of the characteristics of the optical image, and generate a synthesized image by synthesizing the image signal on which distortion-correction has been performed and the image signal of the non-distortion-correction region.

In an aspect, the present disclosure provides a method of providing a dimensionally aware prediction for an object in an image captured by an image sensor, using a scale selective machine learning system, comprising: obtaining an input comprising image data of an object at an input image scale; generating a plurality of variant images based on re-scaling the input with a plurality of different image scaling factors, each variant image comprising the object at a variant image scale; generating a plurality of scale selective predictions based on the plurality of variant images, and assigning an in-scope response when the variant image comprises the object at an in-scope image scale, and determining a location prediction for the object based on a scale selective prediction comprising the in-scope response.

A method for performing multi-functional image restoration by an electronic device with a trained Machine Learning (ML) model is provided. The method includes receiving an image and determining channels of the image, and determining whether a number of restructuring needed for the channels is one. When the restructuring needed for the channels not one, then the method includes restructuring each channel into a first channel set, generating first inferences of the image corresponding to each channel by feeding the first channel set to the trained ML model, and generating a final inference image by combining the first inferences. When the number of restructuring needed for the channels is one, then the method includes restructuring the channels into a second channel set, and generating a second inference of the image by feeding the second channel set to the trained ML model.