Patents by Inventor Eugene Inghaw Shih
Eugene Inghaw Shih has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 10217218Abstract: In an embodiment, a method converts two images to a transform representation in a transform domain. For each spatial position, the method examines coefficients representing a neighborhood of the spatial position that is spatially the same across each of the two images. The method calculates a first vector in the transform domain based on first coefficients representing the spatial position, the first vector representing change from a first to second image of the two images describing deformation. The method modifies the first vector to create a second vector in the transform domain representing amplified movement at the spatial position between the first and second images. The method calculates second coefficients based on the second vector of the transform domain. From the second coefficients, the method generates an output image showing motion amplified according to the second vector for each spatial position between the first and second images.Type: GrantFiled: May 17, 2018Date of Patent: February 26, 2019Assignees: Massachusetts Institute of Technology, Quanta Computer Inc.Inventors: Hao-yu Wu, Michael Rubinstein, Eugene Inghaw Shih, John V. Guttag, Frederic Durand, William T. Freeman, Neal Wadhwa
-
Publication number: 20180268543Abstract: In an embodiment, a method converts two images to a transform representation in a transform domain. For each spatial position, the method examines coefficients representing a neighborhood of the spatial position that is spatially the same across each of the two images. The method calculates a first vector in the transform domain based on first coefficients representing the spatial position, the first vector representing change from a first to second image of the two images describing deformation. The method modifies the first vector to create a second vector in the transform domain representing amplified movement at the spatial position between the first and second images. The method calculates second coefficients based on the second vector of the transform domain. From the second coefficients, the method generates an output image showing motion amplified according to the second vector for each spatial position between the first and second images.Type: ApplicationFiled: May 17, 2018Publication date: September 20, 2018Inventors: Hao-yu Wu, Michael Rubinstein, Eugene Inghaw Shih, John V. Guttag, Frederic Durand, William T. Freeman, Neal Wadhwa
-
Patent number: 10007986Abstract: In an embodiment, a method converts two images to a transform representation in a transform domain. For each spatial position, the method examines coefficients representing a neighborhood of the spatial position that is spatially the same across each of the two images. The method calculates a first vector in the transform domain based on first coefficients representing the spatial position, the first vector representing change from a first to second image of the two images describing deformation. The method modifies the first vector to create a second vector in the transform domain representing amplified movement at the spatial position between the first and second images. The method calculates second coefficients based on the second vector of the transform domain. From the second coefficients, the method generates an output image showing motion amplified according to the second vector for each spatial position between the first and second images.Type: GrantFiled: September 29, 2017Date of Patent: June 26, 2018Assignees: MASSACHUSETTS INSTITUTE OF TECHNOLOGY, QUANTA COMPUTER, INC.Inventors: Hao-yu Wu, Michael Rubinstein, Eugene Inghaw Shih, John V. Guttag, Frederic Durand, William T. Freeman, Neal Wadhwa
-
Publication number: 20180047160Abstract: In an embodiment, a method converts two images to a transform representation in a transform domain. For each spatial position, the method examines coefficients representing a neighborhood of the spatial position that is spatially the same across each of the two images. The method calculates a first vector in the transform domain based on first coefficients representing the spatial position, the first vector representing change from a first to second image of the two images describing deformation. The method modifies the first vector to create a second vector in the transform domain representing amplified movement at the spatial position between the first and second images. The method calculates second coefficients based on the second vector of the transform domain. From the second coefficients, the method generates an output image showing motion amplified according to the second vector for each spatial position between the first and second images.Type: ApplicationFiled: September 29, 2017Publication date: February 15, 2018Applicant: Quanta Computer, Inc.Inventors: Hao-yu Wu, Michael Rubinstein, Eugene Inghaw Shih, John V. Guttag, Frederic Durand, William T. Freeman, Neal Wadhwa
-
Patent number: 9811901Abstract: In one embodiment, a method of amplifying temporal variation in at least two images comprises examining pixel values of the at least two images. The temporal variation of the pixel values between the at least two images can be below a particular threshold. The method can further include applying signal processing to the pixel values.Type: GrantFiled: March 26, 2013Date of Patent: November 7, 2017Assignees: Massachusetts Institute of Technology, Quanta Computer Inc.Inventors: Hao-yu Wu, Michael Rubinstein, Eugene Inghaw Shih, John V. Guttag, Frederic Durand, William T. Freeman
-
Patent number: 9805475Abstract: In one embodiment, a method of amplifying temporal variation in at least two images includes converting two or more images to a transform representation. The method further includes, for each spatial position within the two or more images, examining a plurality of coefficient values. The method additionally includes calculating a first vector based on the plurality of coefficient values. The first vector can represent change from a first image to a second image of the at least two images describing deformation. The method also includes modifying the first vector to create a second vector. The method further includes calculating a second plurality of coefficients based on the second vector.Type: GrantFiled: September 7, 2012Date of Patent: October 31, 2017Assignees: Massachusetts Institute of Technology, Quanta Computer Inc.Inventors: Michael Rubinstein, Neal Wadhwa, Frederic Durand, William T. Freeman, Hao-yu Wu, Eugene Inghaw Shih, John V. Guttag
-
Patent number: 9324005Abstract: In one embodiment, a method of amplifying temporal variation in at least two images includes converting two or more images to a transform representation. The method further includes, for each spatial position within the two or more images, examining a plurality of coefficient values. The method additionally includes calculating a first vector based on the plurality of coefficient values. The first vector can represent change from a first image to a second image of the at least two images describing deformation. The method also includes modifying the first vector to create a second vector. The method further includes calculating a second plurality of coefficients based on the second vector.Type: GrantFiled: December 6, 2012Date of Patent: April 26, 2016Assignee: Massachusetts Institute of Technology Quanta Computer Inc.Inventors: Neal Wadhwa, Michael Rubinstein, Frederic Durand, William T. Freeman, Hao-Yu Wu, Eugene Inghaw Shih, John V. Guttag
-
Publication number: 20140267919Abstract: Techniques are disclosed to process certain information contained in a digital video signal. In particular, a time-varying signal present in the digit video signal may be supplanted with a replacement time-varying signal, negated, or obfuscated with a noise signal. Negation of the time-varying signal may include extracting said time-varying signal from the digital video signal, inverting the time-varying signal, and adding the inverted time-varying signal to the original digital video signal. Obfuscation of the time-varying signal may be accomplished by introducing a suitable noise signal to the original digital video signal. Supplanting the time-varying signal with a replacement signal may include negating the time-varying signal and introducing a desired replacement signal to the digital video signal.Type: ApplicationFiled: March 15, 2013Publication date: September 18, 2014Applicant: QUANTA COMPUTER, INC.Inventors: Steven Keith HELLER, Eugene Inghaw SHIH
-
Publication number: 20140072190Abstract: In one embodiment, a method of amplifying temporal variation in at least two images comprises examining pixel values of the at least two images. The temporal variation of the pixel values between the at least two images can be below a particular threshold. The method can further include applying signal processing to the pixel values.Type: ApplicationFiled: March 26, 2013Publication date: March 13, 2014Applicant: Massachusetts Institute of TechnologyInventors: Hao-yu Wu, Michael Rubinstein, Eugene Inghaw Shih, John V. Guttag, Frederic Durand, William T. Freeman