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.

Some example embodiments relate to a super resolution scanning electron microscope (SEM) image implementing device and/or a method thereof. Provided a super resolution scanning electron microscope (SEM) image implementing device comprising a processor configured to crop a low resolution SEM image to generate a first cropped image and a second cropped image, to upscale the first cropped image and the second cropped image to generate a first upscaled image and a second upscaled image, and to cancel noise from the first upscaled image and the second upscaled image to generate a first noise canceled image and a second noise canceled image.

Disclosed is a ray clustering learning method based on weakly-supervised learning for denoising using ray tracing. The ray clustering learning method is for learning a denoising model for removing noise from a rendered image through ray tracing, and includes extracting a feature of a simulated ray through the ray tracing and clustering the ray through contrastive learning for the feature.

An image is received from a camera built into a cabin of a vehicle. The image is demosaiced and its noise is reduced. A segmentation algorithm is applied to the image. A global illumination for the image is solved. Based on the segmentation of the image and the global illumination, a bidirectional reflectance distribution function (BRDF) for color and/or reflectance information of material in the cabin area of the vehicle is solved for. A white balance matrix and a color correction matrix for the image are computed based on the BRDF. The white balance matrix and the color correction matrix are applied to the image, which is then displayed or stored for addition image processing.

A method of an electronic device including obtaining a low-resolution input image by down-sampling a high-resolution input image; obtaining a low-resolution output image by performing image quality processing on the low-resolution input image; obtaining a low-resolution model from a conversion relationship between the low-resolution input image prior to the image quality processing being performed and the low-resolution output image subsequent to the image quality processing being performed; performing up-sampling of the low-resolution model; obtaining a high-resolution model by modifying the up-sampled low-resolution model, based on a difference between the high-resolution input image and the low-resolution input image; and obtaining a high-resolution output image from the high-resolution input image, by applying the high-resolution model to the high-resolution input image.

One embodiment provides a method generating a first image crop and a second image crop randomly extracted from a low-quality image and a high-quality image, respectively. The method further comprises comparing the first image crop and the second image crop using a plurality of loss functions including pixel-wise loss to calculate losses, and optimizing a model trained to estimate a realistic scale-independent blur kernel of a low-resolution (LR) blurred image by minimizing the losses.

The ultrasonic diagnostic apparatus according to the present embodiment includes processing circuitry. The processing circuitry is configured to: acquire multiple position data associated with respective multiple two-dimensional image data of ultrasonic related to multiple cross sections; smooth the acquired multiple position data; and arrange the multiple two-dimensional image data in accordance with the smoothed multiple position data to generate volume data.

A neural network-based rendering technique increases temporal stability and image fidelity of low sample count path tracing by optimizing a distribution of samples for rendering each image in a sequence. A sample predictor neural network learns spatio-temporal sampling strategies such as placing more samples in dis-occluded regions and tracking specular highlights. Temporal feedback enables a denoiser neural network to boost the effective input sample count and increases temporal stability. The initial uniform sampling step typically present in adaptive sampling algorithms is not needed. The sample predictor and denoiser operate at interactive rates to achieve significantly improved image quality and temporal stability compared with conventional adaptive sampling techniques.

The present disclosure provides a method for incrementing a sample image, an electronic device, and a computer readable storage medium. A specific implementation comprises: acquiring a first convolutional feature of an original sample image; determining, according to a region generation network and the first convolutional feature, a candidate region and a first probability that the candidate region contains a target object; determining a target candidate region from the candidate region based on the first probability, and mapping the target candidate region back to the original sample image to obtain an intermediate image; and performing image enhancement processing on a portion of the intermediate image corresponding to the target candidate region and/or performing image blur processing on a portion of the intermediate image corresponding to a non-target candidate region to obtain an incremental sample image.

The invention provides for a medical apparatus (100, 300, 400) comprising a subject support (102) configured for moving a subject (106) from a first position (124) to a second position (130) along a linear path (134). The subject support comprises a support surface (108) for receiving the subject. The subject support is further configured for positioning the subject support in at least one intermediate position (128). The subject support is configured for measuring a displacement (132) along the linear path between the first position and the at least one intermediate position. Each of the at least one intermediate position is located between the first position and the second position. The medical apparatus further comprises a camera (110) configured for imaging the support surface in the first position. Execution of machine executable instructions 116 cause the a processor (116) controlling the medical apparatus to: acquire (200) an initial image (142) with the camera when the subject support is in the first position; control (202) the subject support to move the subject support from the first position to the second position; acquire (204) at least one intermediate image (144) with the camera and the displacement for each of the at least one intermediate image as the subject support is moved from the first position to the second position; and calculate (206) a height profile (150, 600, 604) of the subject by comparing the initial image and the at least one intermediate image. The height profile is at least partially calculated using the displacement. The height profile is descriptive of the spatially dependent height of the subject above the support surface.