A method includes capturing, by a camera disposed behind a display panel of an electronic device, an original image through a semi-transparent pixel region of the display panel. The original image includes one or more color components. The method further includes determining, for a plurality of pixel regions of the original image, a point spread function (PSF) for each of the one or more color components. The method further includes performing, for the plurality of pixel regions of the original image, a deconvolution of each of the one or more color components of the original image based at least in part on their respective PSFs. The method thus includes generating a reconstructed image corresponding to the original image based on the deconvolutions of the one or more color components of the plurality of pixel regions of the original image.

In one embodiment, a method includes obtaining an image comprising a plurality of pixels, determining, for a particular pixel of the plurality of pixels, a gradient value, classifying, based on the gradient value, the particular pixel into a flat class or one of a plurality of edge classes, and denoising the particular pixel based on the classification.

Disclosed is a system to add photorealistic detail and motion to an image based on a first material property associated with a first set of data points of an incomplete first object, and a second material property associated with a second set of data points of an incomplete second object in the image. The system may generate first artificial data points amongst the first set of data points that completes a first arrangement defined for the first material property, and may generate second artificial data points amongst the second set of data points that completes a second arrangement defined for the second material property. The system may then output an enhanced image of the completed first object based on first set of data points and the first artificial data points, and of the completed second object based on the second set of data points and the second artificial data points.

Aspects of the present disclosure involve a system and a method for performing operations comprising: displaying, by a messaging application, a sound capture screen that enables a user to record the sound; after the sound is recorded using the sound capture screen, generating, by the messaging application, a visual element associated with the sound; receiving, by the messaging application, selection of the visual element from a displayed list of visual elements representing different sounds; in response to receiving the selection of the visual element, conditionally adding one or more graphics representing the sound to one or more images at a user selected position based on a privacy status of the sound; and playing, by the messaging application, the sound associated with the visual element together with displaying the one or more images.

A specimen processing system includes a plate for supporting a specimen system, wherein the specimen system includes a container and a specimen contained therein. The specimen processing system further includes a camera disposed above the plate and configured to generate images of the specimen system, a light source disposed beneath the plate for radiating light towards the plate, a light stop for blocking a portion of the light from reaching the specimen system to produce darkfield illumination of the specimen at the camera, and one or more processors electronically coupled to the camera and configured to track a position of the specimen within the specimen container during a specimen processing protocol based on the images.

Disclosed are various examples for selective screen sharing. In one example, a computing device can generate a video stream based on a screen capture and transmit the video stream to a destination device. The computing device can also obtain a user-specified modification to an area of the screen capture within the video stream. The computing device can also update the video stream by application of a transformation to the screen capture based at least in part on the user-specified modification, after the video stream started transmission to the destination device. In some cases, a user-specified modification to the area is also obtained. The video stream can be updated by applying an updated transformation to the screen capture that obscures the updated area within the video stream.

To enable a high quality HDR video communication, which can work by sending corresponding LDR images potentially via established LDR video communication technologies, which works well in practical situations, applicant has invented a HDR video decoder (600, 1100) arranged to calculate a HDR image (Im_RHDR) based on applying to a received 100 nit standard dynamic range image (Im_RLDR) a set of luminance transformation functions, the functions comprising at least a coarse luminance mapping (FC), which is applied by a dynamic range optimizer (603), and a mapping of the darkest value (0) of an intermediate luma (Y′HPS), being output of the dynamic range optimizer, to a received black offset value (Bk_off) by a range stretcher (604), the video decoder comprising a gain limiter (611, 1105) arranged to apply an alternate luminance transformation function to calculate a subset (502) of the darkest luminances of the HDR image, from corresponding darkest lumas (Y′_in) of the standard dynamic range image.

The present disclosure relates to systems, non-transitory computer-readable media, and methods that utilize a progressive refinement network to refine alpha mattes generated utilizing a mask-guided matting neural network. In particular, the disclosed systems can use the matting neural network to process a digital image and a coarse guidance mask to generate alpha mattes at discrete neural network layers. In turn, the disclosed systems can use the progressive refinement network to combine alpha mattes and refine areas of uncertainty. For example, the progressive refinement network can combine a core alpha matte corresponding to more certain core regions of a first alpha matte and a boundary alpha matte corresponding to uncertain boundary regions of a second, higher resolution alpha matte. Based on the combination of the core alpha matte and the boundary alpha matte, the disclosed systems can generate a final alpha matte for use in image matting processes.

A method for point cloud decoding includes receiving a bitstream. The method also includes decoding the bitstream into multiple frames that include pixels. Certain pixels of the multiple frames correspond to points of a three-dimensional (3D) point cloud. The multiple frames include a first set of frames that represent locations of the points of the 3D point cloud and a second set of frames that represent attribute information for the points of the 3D point cloud. The method further includes reconstructing the 3D point cloud based on the first set of frames. Additionally, the method includes identifying a first portion of the points of the reconstructed 3D point cloud based at least in part on a property associated with the multiple frames. The method also includes modifying a portion of the attribute information. The portion of the attribute information that is modified corresponds to the first portion of the points.

Disclosed herein is an X-ray apparatus for acquiring a medical image, and a method of using said X-ray apparatus, said method comprising the steps of: acquiring an original radiation image of a target object and capturing condition information of the object; acquiring a scatter radiation image related to the original radiation image by inputting the original radiation image and the capturing condition information to a learning network model configured to estimate scatter radiation; and acquiring a scatter radiation-processed medical image from the original radiation image on the basis of the original radiation image and the scatter radiation image, wherein the learning network model configured to estimate scatter radiation is a learning network model taught using a plurality of scatter radiation images and a plurality of pieces of capturing condition information related to each of the plurality of scatter radiation images.