Aspects of the present disclosure relate to systems, devices and methods for performing a surgical step or surgical procedure for example with visual guidance using a head mounted display or with a surgical navigation system or with a surgical robot. A computer processor can be configured to determine the pose of a first vertebra with an attached first marker and a second vertebra with an attached second marker. The computer processor can be configured to determine the pose of at least one vertebra interposed or adjacent to the first and second vertebrae with attached markers, e.g. fiducial markers.

A neural network feature decoding method and apparatus according to the present disclosure receives a bitstream including an encoded feature, decodes a feature from a bitstream, and reconstructs features corresponding to a plurality of layers of a neural network based on a decoded feature.

An information processing apparatus that functions as a non-limiting example image processing apparatus includes a processor. When an original image drawn with horizontally-long first pixels is to be drawn by square second pixels, the processor generates two intermediate image data in each of which the number of second pixels is 1.2 times the number of first pixels of the original image data, by generating a second area formed with six (6) second pixels arranged in a horizontal direction for each of first areas that are formed dividing the original image by every five (5) first pixels arranged in the horizontal direction, and outputs the two intermediate image data to a display control device. The display control device generates output image data by synthesizing the two intermediate image data, and outputs the generated output image data to a display. The output image data is generated in each of the second areas with colors that include colors of the second pixels at both ends, which are in agreement with colors of the first pixels at both ends in each corresponding first area and colors of the second pixels other than the both ends, each of which is generated based on colors of adjacent two first pixels in corresponding first area.

A method for establishing a 3D medical imaging model of a subject is to be implemented by an X-ray computed tomography (CT) scanner and a processor. The method includes: emitting X-rays on the subject sequentially from plural angles with respect to the subject to obtain M number of X-ray images of the subject in sequence; obtaining, for each pair of consecutive X-ray images, K number of intermediate image(s) by using the pair of consecutive X-ray images as inputs to a convolutional neural network (CNN) model that has been trained for frame interpolation; and establishing the 3D medical imaging model by using a 3D reconstruction technique based on the M number of X-ray images and the intermediate images obtained for the M number of X-ray images.

Disclosed are an image processing method and device using a line-wise operation. The image processing device, according to one embodiment, comprises: a receiver for receiving an image; a first convolution operator for generating a feature map by performing a convolution operation on the basis of the image; and a compressor for compressing the feature map into units of at least one line; and a decompressor for reconstructing the feature map compressed into units of lines.

A direct structured illumination microscopy (dSIM) reconstruction method is provided. First, a time domain modulation signal is extracted through a wavelet. Then, an incoherent signal is converted into a coherent signal. Next, an accumulation amount at each pixel is calculated. Finally, a super-resolution image is generated by using a correlation between signals at different spatial positions. An autocorrelation algorithm of dSIM is insensitive to an error of a reconstruction parameter. dSIM bypasses a complex frequency domain operation in structured illumination microscopy (SIM) image reconstruction, and prevents an artifact caused by the parameter error in the frequency domain operation. The dSIM algorithm has high adaptability and can be used in laboratory SIM, nonlinear SIM imaging systems, or commercial systems.

The present disclosure relates to image processing systems and methods. The method may include obtaining a first image and a second image. The first image may be captured by a first camera lens of a panorama device and the second image may be captured by a second camera lens of the panorama device. The method may also include performing an interpolation based on a center of the first image to obtain a first rectangular image, and performing an interpolation based on a center of the second image to obtain a second rectangular image. The method may further include generating a fused image based on the first rectangular image and the second rectangular image, and mapping the fused image to a spherical panorama image.

[Object] Provided is an information processing apparatus that is able to provide consistent image quality even if a distance from a display apparatus varies within a projection region. [Solving Means] The information processing apparatus according to an embodiment of the present disclosure includes a transformation matrix calculation section, a scale calculation section, and an input display generation section. The transformation matrix calculation section calculates a transformation matrix that converts the coordinates of an input position of an input device within a projection region projected from a display apparatus from the coordinates of an image coordinate system of a sensor apparatus having detected the input position to the coordinates of a screen coordinate system of the display apparatus. The scale calculation section calculates a scale correction value for a display mode of the locus of the input position in reference to distance information regarding the distance between the display apparatus and the input position. The input display generation section generates an input image depicting the locus of the input position through the use of the transformation matrix and the scale correction value.

An information processing apparatus includes an interpolation target color difference pixel generator that generates, on the basis of a relationship between a luminance pixel at an interpolation target pixel position that is a pixel position at which a first color difference pixel does not exist and the luminance pixel at at least one neighboring pixel position of a plurality of pixel positions near the interpolation target pixel position in image data, an interpolation target color difference pixel corresponding to the first color difference pixel at the interpolation target pixel position, in which the image data is generated on the basis of three primary color pixels that can include a value greater than a predetermined white clip value, the image data having a number of the luminance pixels larger than a number of the first color difference pixels and a number of second color difference pixels.

A method for applying adaptive zoom on an image is disclosed. The method includes detecting at least one input to perform zoom on the image, determining key pixels in the image, obtaining a plurality of segments by determining sizes of each of the plurality of the segments based on a number of the key pixels in each of the plurality of the segments, determining a priority order for zooming the plurality of the segments based on a density of the key pixels in each of the plurality of the segments, determining a zoom level to be applied on each of the plurality of the segments based on the density of the key pixels in each of the plurality of the segments, and adaptively zooming each of the plurality of the segments based on the zoom level and the priority order.