Mitsubishi Electric Research Laboratories, Inc.

Terarecon, Inc.

Disney Enterprises, Inc.

Mitsubishi Electric Research Labs.

Harvard College

Mitsubishi Electric Information Technology Center America, Inc.

Mitsubishi Electric Information Technology Center America, Inc (ita)

Ichilov Tech Ltd.

Trrarecon, Inc.

Mitsubishi Electric Corporation

Hanspeter Pfister

Wojciech Matusik

Markus H Gross

Matthias Zwicker

James M Knittel

Hugh C Lauer

Jeroen Van Baar

Jan C Hardenbergh

Randy B Osborne

Collin E Oosterbaan

Baback Moghaddam

Jinho Lee

Wai Kit Addy Ngan

Leonard McMillan, Jr

Drew R Martin

Joseph W Marks

Raghu Machiraju

Urs H Kanus

Anthony Vetro

Sehoon Yea

Kevin Kreeger

Paul A Beardsley

Bernd Bickel

Chia Shen

Fredo Durand

Takahide Ohkami

Christopher J Kappler

Miguel A Otaduy

William R Peet

Liu Ren

Remo Ziegler

Michael D Breitenstein

Stephen R Burgess

Frederic H Mokren

Tim Weyrich

Kalyan Krishna Sunkavalli

Markus Gross

Wei Ye Chen

Tiecheng T Zhao

Daniel Vlasic

Sarah F Gibson

Ingmar Bitter

Morgan S McGuire

Sasha Anna Schriber

Kenneth W Correll

Szymon Marek Rusinkiewicz

Vishal C Bhatia

Daniel Needleman

Marcel Germann

Stephan Würmlin

Jay C Wilkinson

John F Hughes

In Kyu Park

Edouard Lamboray

Henrik Wann Jensen

Dalit Ben Yosef

Yu Yang

Matthew M Loper

Nam Wook Kim

Brian Leahy

Marcel German

Stephen F Mason

Beverly J Schultz

Abhir Hari Balerao

Frank Clare Dachille

Michael Waschbüsch

Won-Dong Jang

Embodiments described herein use deep learning to automate measurement of key morphokinetic embryo features associated with viability and quality, in particular those relevant for clinical in-vitro fertilization (IVF). Systems and methods may, for example, acquire one or more digital images of one or more embryos; select one or more embryos in each digital image; and for each selected embryo, (i) computationally characterize the zona pellucida, detect the degree of fragmentation in the embryo, and for each embryo with a low fragmentation score, computationally classify the embryo's developmental stage based on whether cells constituting the embryo exceed a threshold number (e.g., nine). For an embryo consisting of a single cell, pronuclei may be detected and counted. Based on these measurements, a viability score may be assigned to the embryo.

Automated analysis and selection of human embryos

According to one implementation, a narrative visualization system includes a computing platform having a hardware processor and a system memory storing a narrative visualization software code. The hardware processor is configured to execute the narrative visualization software code to receive multiple media files. For each of the media files, the hardware processor is further configured to execute the narrative visualization software code to parse the media file to identify a primary content and metadata describing the primary content, to analyze the metadata to determine representative features of the primary content, and to generate a visualization of the primary content based on the metadata and the representative features. The visualization depicts a temporal flow of the primary content in a story tune of the primary content in apposition to a temporal flow of the primary content in a narrative time of the primary content.

Narrative visualization system

In an object generation system, consumable base materials are characterized in a characterization process wherein an object generation system can use a plurality of so-characterized base materials. User input representing a desired object and set of characteristics for that desired object are processed, using a computer or computing device, to derive a mapping of locations for placement of portions of the plurality of base materials such that when the mapping is provided to an object generator, the generated object approximates the representing a desired object and set of characteristics. The characterization of a base material might include elasticity of the base material, the user input might be a desired shape and elasticity, the object generator might be a 3D multi-material printer and the generated object might at least approximate the desired shape and elasticity as a result of being constructed from the plurality of base materials used by the printer.

Fabrication of materials with desired characteristics from base materials having determined characteristics

A method and system acquire and display light fields. A continuous light field is reconstructed from input samples of an input light field of a 3D scene acquired by cameras according to an acquisition parameterization. The continuous light is reparameterized according to a display parameterization and then prefiltering and sampled to produce output samples having the display parametrization. The output samples are displayed as an output light field using a 3D display device. The reconstruction can be performed by interpolating the input samples having the different views.

Method and system for decoding and displaying 3D light fields

A method and system acquire and display light fields. A continuous light field is reconstructed from input samples of an input light field of a 3D scene acquired by cameras according to an acquisition parameterization. The continuous light is reparameterized according to a display parameterization and then prefiltering and sampled to produce output samples having the display parameterization. The output samples are displayed as an output light field using a 3D display device. The reconstruction can be performed by interpolating the input samples having the different views.

Method and system for acquiring, encoding, decoding and displaying 3D light fields

A method and system determines a pose of an object by comparing an input range image acquired of a scene including the input object to each of a set of reference range image of a reference object, such that each reference range images has an associated different pose, and the reference object is similar to the input object. Then, the pose associated with the reference range image which best matches the input range image is selected as the pose of the input object.

Method and system for determining objects poses from range images

A method for determining a pose of an object from a range image is presented. A distribution of poses for an object is determined from a model of the object. A set of reference poses is selected according to the distribution, such that more reference poses are selected for more probable poses than less probable poses. A reference image for each reference pose is generated, and the reference pose used to generate the reference image that best matches a range image including the object is assigned as the pose of the object.

Method and system for determining poses of objects from range images using adaptive sampling of pose spaces

A method factorizing a sequence of images acquired of a scene into lighting components. The scene is illuminated by a moving light source. An appearance profile is constructed for each pixel in the sequence of images. The appearance profile is a vector representing intensities of the pixel at instances in time. The appearance profiles are factorized into a shadow component, a skylight component, and a sunlight component.

System and method for factorizing light in a sequence of images

A method recognizes a face in an image. A morphable model having shape and pose parameters is fitted to a face in an image to construct a three-dimensional model of the face. Texture is extracted from the face in the image using the three-dimensional model. The shape and texture are projected into a bilinear illumination model to generate illumination bases for the face in the image. The illumination bases for the face in the image are compared to illumination bases of each of a plurality of bilinear illumination models of known faces to identify the face in the image.

Bilinear illumination model for robust face recognition

A method and system acquire and display light fields. A continuous light field is reconstructed from input samples of an input light field of a 3D scene acquired by cameras according to an acquisition parameterization. The continuous light is reparameterized according to a display parameterization and then prefiltering and sampled to produce output samples having the display parametrization. The output samples are displayed as an output light field using a 3D display device.

Method and system for acquiring and displaying 3D light fields

A method generates a three-dimensional, bi-linear, illumination model for arbitrary faces. A large number of images are acquired of many different faces. For each face, multiple images are acquired with varying poses and varying illumination. A three-mode singular value decomposition is applied to the images to determine parameters of the model. The model can be fit to a probe image of an unknown face. Then, the model can be compared with models of a gallery of images of unknown faces to recognize the face in the probe image.

Method and system for generating bi-linear models for faces

A method compresses a set of correlated signals by first converting each signal to a sequence of integers, which are further organized as a set of bit-planes. An inverse accumulator is applied to each bit-plane to produce a bit-plane of shifted bits, which are permuted according to a predetermined permutation to produce bit-planes of permuted bits. Each bit-plane of permuted bits is partitioned into a set of blocks of bits. Syndrome bits are generated for each block of bits according to a rate-adaptive base code. Subsequently, the syndrome bits are decompressed in a decoder to recover the original correlated signals.

System and method for image matting

A method determines an optimal set of viewpoints to acquire a 3D shape of a face. A view-sphere is tessellated with a plurality of viewpoint cells. The face is at an approximate center of the view-sphere. Selected viewpoint cells are discarded. The remaining viewpoint cells are clustered to a predetermined number of viewpoint cells according to a silhouette difference metric. The predetermined number of viewpoint cells are searched for a set of optimal viewpoint cells to construct a 3D model of the face.

Method for determining optimal viewpoints for 3D face modeling and face recognition

A system encodes videos acquired of a moving object in a scene by multiple fixed cameras. Camera calibration data of each camera are first determined. The camera calibration data of each camera are associated with the corresponding video. A segmentation mask for each frame of each video is determined. The segmentation mask identifies only foreground pixels in the frame associated with the object. A shape encoder then encodes the segmentation masks, a position encoder encodes a position of each pixel, and a color encoder encodes a color of each pixel. The encoded data can be combined into a single bitstream and transferred to a decoder. At the decoder, the bitstream is decoded to an output video having an arbitrary user selected viewpoint. A dynamic 3D point model defines a geometry of the moving object. Splat sizes and surface normals used during the rendering can be explicitly determined by the encoder, or explicitly by the decoder.

Method for encoding and decoding free viewpoint videos

Growing community of inventors

Arlington, MA, United States of America

Hanspeter Pfister