Samsung Electronics Co., Ltd.

Nvidia Corporation

Dmitry Korobchenko

Praveen Gulaka

Mikhail Yurievich Sirotenko

Alexey Bronislavovich Danilevich

Mikhail Nikolaevich Rychagov

Alexey Solovey

Evgenii Tumanov

Sang-cheon Choi

Artem Sergeevich Migukin

Yang Lim Choi

Simon Yuen

Evgeny Aleksandrovich Tumanov

Kevin Margo

Michail Nikolaevich Rychagov

Sergey Konstantinovich Ternovoy

Merab Archil'evich Sharia

Kirill Arthurovich Gavrilyuk

Dmitry Vladimirovich Ustuzhanin

In various examples, animations may be generated using audio-driven body animation synthesized with voice tempo. For example, full body animation may be driven from an audio input representative of recorded speech, where voice tempo (e.g., a number of phonemes per unit time) may be used to generate a 1D audio signal for comparing to datasets including data samples that each include an animation and a corresponding 1D audio signal. One or more loss functions may be used to compare the 1D audio signal from the input audio to the audio signals of the datasets, as well as to compare joint information of joints of an actor between animations of two or more data samples, in order to identify optimal transition points between the animations. The animations may then be stitched together—e.g., using interpolation and/or a neural network trained to seamlessly stitch sequences together—using the transition points.

Synthetic audio-driven body animation using voice tempo

Approaches in accordance with various embodiments provide for fluid simulation with substantially reduced time and memory requirements with respect to conventional approaches. In particular, various embodiments can perform time and energy efficient, large scale fluid simulation on processing hardware using a method that does not solve for the Navier-Stokes equations to enforce incompressibility. Instead, various embodiments generate a density tensor and rigid body map tensor for a large number of particles contained in a sub-domain. Collectively, the density tensor and rigid body map may represent input channels of a network with three spatial-dimensions. The network may apply a series of operations to the input channels to predict an updated position and updated velocity for each particle at the end of a frame. Such approaches can handle tens of millions of particles within a virtually unbounded simulation domain, as compared to classical approaches that solve for the Navier-Stokes equations.

Fluid simulations using one or more neural networks

Provided is a magnetic resonance imaging (MRI) apparatus including an acquisition unit configured to acquire an undersampled spectrum in a k-space and a reconstruction unit configured to generate a target image based on the undersampled spectrum, wherein the reconstruction unit includes: a first sub-reconstruction unit configured to perform initial reconstruction on data corresponding to unsampled positions in the k-space by using a Split Bregman algorithm or approximate sparse coding; a second sub-reconstruction unit configured to decompose the initially reconstructed spectrum in the k-space into multiple frequency bands to thereby generate a plurality of individual spectra and perform dictionary learning reconstruction on images respectively corresponding to the decomposed multiple frequency bands by alternating sparse approximation and reconstructing of measured frequencies; and an image generator configured to generate a target image by merging together the reconstructed images respectively corresponding to the multiple frequency bands.

Magnetic resonance imaging device and method for generating magnetic resonance image

A method of automatically registering landmarks in a 3-dimensional (3D) medical image includes obtaining a 3D image; determining a set of search points based on a statistical atlas attached to a bounding box corresponding to a part of the 3D image; extracting features of the determined set of search points; forming a set of candidates for a landmark based on the extracted features; filtering the candidates and outputting remaining candidates among the candidates based on the filtering; and outputting a final position of the landmark based on one of the remaining candidates.

Apparatus and method for automatically registering landmarks in three-dimensional medical image

A method of automatic planning of a view in a 3D image of a brain includes A method of automatic planning a view in a three-dimensional (3D) image of a brain includes selecting a plurality of axial working sections and a plurality of coronal working sections in the 3D scout image; constructing at least one mid-sagittal plane of the brain based on a set of axial reference lines and a set of coronal reference lines obtained from the selected plurality of axial working sections and the selected plurality of coronal working sections, respectively; detecting at least one landmark that is an anatomical point in the at least one mid-sagittal plane; creating a first reference line based on the at least one landmark detected in the at least one mid-sagittal plane; and planning a scan in an orientation based on the at least one mid-sagittal plane and the first reference line.

System and method for automatic planning of views in 3D images of brain

Provided is medical equipment and a technique for analyzing medical images. A method for automatically planning views in three-dimensional (3D) medical images includes: estimating a statistical model indicating positions of anatomical points, the statistical model having parameters calculated by minimizing energy of a loss function; training an anatomical point detector to detect the plurality of anatomical points by using the estimated statistical model; acquiring a 3D image having a region of interest; detecting a set of candidates of the anatomical points in the 3D image; searching the set of candidates for an optimal configuration corresponding to the plurality of anatomical points; and forming a view plane based on the optimal configuration found by the searching.

System and method for automatic planning of two-dimensional views in 3D medical images

Growing community of inventors

Moscow, Russia

Dmitry Korobchenko