Various methods and systems are provided for artifact reduction with resolution preservation. In one example, a method includes obtaining projection data of an imaging subject, identifying a metal-containing region in the projection data, interpolating the metal-containing region to generate interpolated projection data, extracting high frequency content information from the projection data in the metal-containing region, adding the extracted high frequency content information to the interpolated projection data to generate adjusted projection data, and reconstructing one or more diagnostic images from the adjusted projection data.

A 3-D convolutional autoencoder for low-dose CT via transfer learning from a 2-D trained network is described, A machine learning method for low dose computed tomography (LDCT) image correction is provided. The method includes training, by a training circuitry, a neural network (NN) based, at least in part, on two-dimensional (2-D) training data. The 2-D training data includes a plurality of 2-D training image pairs. Each 2-D image pair includes one training input image and one corresponding target output image. The training includes adjusting at least one of a plurality of 2-D weights based, at least in part, on an objective function. The method further includes refining, by the training circuitry, the NN based, at least in part, on three-dimensional (3-D) training data. The 3-D training data includes a plurality of 3-D training image pairs. Each 3-D training image pair includes a plurality of adjacent 2-D training input images and at least one corresponding target output image. The refining includes adjusting at least one of a plurality of 3-D weights based, at least in part, on the plurality of 2-D weights and based, at least in part, on the objective function. The plurality of 2-D weights includes the at least one adjusted 2-D weight.

Embodiments of the present invention are a high dynamic range (HDR) synthesis method and apparatus, an image processing chip and an aerial camera. The method includes: acquiring a plurality of to-be-synthesized images having different exposure time; calculating a mean brightness of the to-be-synthesized images; determining an image brightness type of the to-be-synthesized images according to the mean brightness; calculating a brightness difference between adjacent pixel points in one to-be-synthesized image; calculating an inter-frame difference of different to-be-synthesized images at a same pixel point position according to the brightness difference; determining a motion state of the to-be-synthesized images at the pixel point position according to the inter-frame difference; and weighting and synthesizing the to-be-synthesized images into a corresponding HDR image according to the image brightness type and the motion state.

An information processing device (200A, 200B, and 200C) according to the present disclosure includes a control unit (220, 220B, and 220C). The control unit (220, 220B, and 220C) acquires a captured image of a target imaged by a sensor. The captured image is an image obtained from reflected light of light emitted to the target from a plurality of light sources arranged at different positions, respectively. The control unit (220, 220B, and 220C) extracts a flat region from the captured image based on a luminance value of the captured image. The control unit (220, 220B, and 220C) calculates shape information regarding a shape of a surface of the target based on information regarding the sensor and the flat region of the captured image.

The present disclosure relates to an image processing apparatus and method capable of suppressing an increase in load of inverse adaptive color transform processing while suppressing an increase in distortion of coefficient data subjected to inverse adaptive color transform.

The coefficient data subjected to the lossless adaptive color transform is clipped at a level based on a bit depth of the coefficient data, and the coefficient data clipped at the level is subjected to lossless inverse adaptive color transform. The present disclosure may be applied to, for example, an image processing apparatus, an image coding device, an image decoding device, a transmission device, a reception device, a transmission/reception device, an information processing device, an imaging device, a reproduction device, an electronic device, an image processing method, an information processing method, or the like.

An image processing method and an image processing unit for performing image processing determines a set of one or more filtered pixel values, wherein the one or more filtered pixel values represent a result of processing image data using a set of one or more filtering functions. A total covariance of the set of one or more filtering functions is identified. A refinement filtering function is applied to the set of one or more filtered pixel values to determine a set of one or more refined pixel values, wherein the refinement filtering function has a covariance that is determined based on the total covariance of the set of one or more filtering functions.

The present disclosure provides an electronic apparatus capable of capturing an image without being affected by an abnormality on a display surface.

The electronic apparatus includes: a display unit; an imaging unit that is disposed on an opposite side to a display surface of the display unit; an abnormality detection unit that detects an abnormality on the display surface; and a display control unit that highlights a position where the abnormality detected by the abnormality detection unit occurs on the display unit.

A computer-implemented method is provided for improving live video quality. The method comprises: acquiring, using a medical imaging apparatus, a stream of consecutive image frames of a subject, and the stream of consecutive image frames are acquired with reduced amount of radiation dose; applying a deep learning network model to the stream of consecutive image frames to generate an image frame with improved quality; and displaying the image frame with improved quality in real-time on a display.

A method includes: computing noise data by subtracting, by a processing circuit, a noisy image from a corresponding ground truth image; clustering, by the processing circuit, a plurality of noise values of the noise data based on intensity values of the corresponding ground truth image; permuting, by the processing circuit, a plurality of locations of the noise values of the noise data within each cluster; generating, by the processing circuit, a synthetic noise image based on the permuted locations of the noise values; adding, by the processing circuit, the synthetic noise image to the corresponding ground truth image to generate a synthetic noisy image; and augmenting an image dataset for training a neural network to perform image denoising with the synthetic noisy image.

A mapping curve parameter obtaining method and apparatus are described. The method includes obtaining a first mapping curve parameter set and first maximum target system display luminance, and obtaining a display luminance parameter set, where the display luminance parameter set includes maximum display luminance and/or minimum display luminance of a display device. The method also includes obtaining an adjustment coefficient set, where the adjustment coefficient set includes one or more adjustment coefficients, and the one or more adjustment coefficients correspond to one or more parameters in the first mapping curve parameter set. Furthermore, the method includes adjusting the one or more parameters in the first mapping curve parameter set based on the display luminance parameter set, the first maximum target system display luminance, and the adjustment coefficient set to obtain a second mapping curve parameter set, where the second mapping curve parameter set includes one or more adjusted parameters.