Patents by Inventor Alexander W. Weiss
Alexander W. Weiss 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: 11501508Abstract: Disclosed are computer-readable devices, systems and methods for generating a model of a clothed body. The method includes generating a model of an unclothed human body, the model capturing a shape or a pose of the unclothed human body, determining two-dimensional contours associated with the model, and computing deformations by aligning a contour of a clothed human body with a contour of the unclothed human body. Based on the two-dimensional contours and the deformations, the method includes generating a first two-dimensional model of the unclothed human body, the first two-dimensional model factoring the deformations of the unclothed human body into one or more of a shape variation component, a viewpoint change, and a pose variation and learning an eigen-clothing model using principal component analysis applied to the deformations, wherein the eigen-clothing model classifies different types of clothing, to yield a second two-dimensional model of a clothed human body.Type: GrantFiled: July 8, 2021Date of Patent: November 15, 2022Assignee: Brown UniversityInventors: Michael J. Black, Oren Freifeld, Alexander W. Weiss, Matthew M. Loper, Peng Guan
-
Publication number: 20210398361Abstract: Disclosed are computer-readable devices, systems and methods for generating a model of a clothed body. The method includes generating a model of an unclothed human body, the model capturing a shape or a pose of the unclothed human body, determining two-dimensional contours associated with the model, and computing deformations by aligning a contour of a clothed human body with a contour of the unclothed human body. Based on the two-dimensional contours and the deformations, the method includes generating a first two-dimensional model of the unclothed human body, the first two-dimensional model factoring the deformations of the unclothed human body into one or more of a shape variation component, a viewpoint change, and a pose variation and learning an eigen-clothing model using principal component analysis applied to the deformations, wherein the eigen-clothing model classifies different types of clothing, to yield a second two-dimensional model of a clothed human body.Type: ApplicationFiled: July 8, 2021Publication date: December 23, 2021Inventors: Michael J. Black, Oren Freifeld, Alexander W. Weiss, Matthew M. Loper, Peng Guan
-
Patent number: 11062528Abstract: Disclosed are computer-readable devices, systems and methods for generating a model of a clothed body. The method includes generating a model of an unclothed human body, the model capturing a shape or a pose of the unclothed human body, determining two-dimensional contours associated with the model, and computing deformations by aligning a contour of a clothed human body with a contour of the unclothed human body. Based on the two-dimensional contours and the deformations, the method includes generating a first two-dimensional model of the unclothed human body, the first two-dimensional model factoring the deformations of the unclothed human body into one or more of a shape variation component, a viewpoint change, and a pose variation and learning an eigen-clothing model using principal component analysis applied to the deformations, wherein the eigen-clothing model classifies different types of clothing, to yield a second two-dimensional model of a clothed human body.Type: GrantFiled: August 19, 2019Date of Patent: July 13, 2021Assignee: BROWN UNIVERSITYInventors: Michael J. Black, Oren Freifeld, Alexander W. Weiss, Matthew M. Loper, Peng Guan
-
Patent number: 10546417Abstract: A system and method of estimating the body shape of an individual from input data such as images or range maps. The body may appear in one or more poses captured at different times and a consistent body shape is computed for all poses. The body may appearin minimal tight-fitting clothing or in normal clothing wherein the described method produces an estimate of the body shape under the clothing. Clothed or bare regions of the body are detected via image classification and the fitting method is adapted to treat each region differently. Body shapes are represented parametrically and are matched to other bodies based on shape similarity and other features. Standard measurements are extracted using parametric or non-parametric functions of body shape. The system components support many applications in body scanning, advertising, social networking, collaborative filtering and Internet clothing shopping.Type: GrantFiled: June 26, 2019Date of Patent: January 28, 2020Assignee: BROWN UNIVERSITYInventors: Michael J. Black, Alexandru O. Balan, Alexander W. Weiss, Leonid Sigal, Matthew M. Loper, Timothy S. St. Clair
-
Publication number: 20190385381Abstract: Disclosed are computer-readable devices, systems and methods for generating a model of a clothed body. The method includes generating a model of an unclothed human body, the model capturing a shape or a pose of the unclothed human body, determining two-dimensional contours associated with the model, and computing deformations by aligning a contour of a clothed human body with a contour of the unclothed human body. Based on the two-dimensional contours and the deformations, the method includes generating a first two-dimensional model of the unclothed human body, the first two-dimensional model factoring the deformations of the unclothed human body into one or more of a shape variation component, a viewpoint change, and a pose variation and learning an eigen-clothing model using principal component analysis applied to the deformations, wherein the eigen-clothing model classifies different types of clothing, to yield a second two-dimensional model of a clothed human body.Type: ApplicationFiled: August 19, 2019Publication date: December 19, 2019Inventors: Michael J. Black, Oren Freifeld, Alexander W. Weiss, Matthew M. Loper, Peng Guan
-
Publication number: 20190333267Abstract: A system and method of estimating the body shape of an individual from input data such as images or range maps. The body may appear in one or more poses captured at different times and a consistent body shape is computed for all poses. The body may appearin minimal tight-fitting clothing or in normal clothing wherein the described method produces an estimate of the body shape under the clothing. Clothed or bare regions of the body are detected via image classification and the fitting method is adapted to treat each region differently. Body shapes are represented parametrically and are matched to other bodies based on shape similarity and other features. Standard measurements are extracted using parametric or non-parametric functions of body shape. The system components support many applications in body scanning, advertising, social networking, collaborative filtering and Internet clothing shopping.Type: ApplicationFiled: June 26, 2019Publication date: October 31, 2019Inventors: Michael J. BLACK, Alexandru O. BALAN, Alexander W. Weiss, Leonid SIGAL, Matthew M. LOPER, Timothy S. ST. CLAIR
-
Patent number: 10388078Abstract: Disclosed are computer-readable devices, systems and methods for generating a model of a clothed body. The method includes generating a model of an unclothed human body, the model capturing a shape or a pose of the unclothed human body, determining two-dimensional contours associated with the model, and computing deformations by aligning a contour of a clothed human body with a contour of the unclothed human body. Based on the two-dimensional contours and the deformations, the method includes generating a first two-dimensional model of the unclothed human body, the first two-dimensional model factoring the deformations of the unclothed human body into one or more of a shape variation component, a viewpoint change, and a pose variation and learning an eigen-clothing model using principal component analysis applied to the deformations, wherein the eigen-clothing model classifies different types of clothing, to yield a second two-dimensional model of a clothed human body.Type: GrantFiled: September 11, 2017Date of Patent: August 20, 2019Assignee: BROWN UNIVERSITYInventors: Michael J. Black, Oren Freifeld, Alexander W. Weiss, Matthew M. Loper, Peng Guan
-
Patent number: 10339706Abstract: A system and method of estimating the body shape of an individual from input data such as images or range maps. The body may appear in one or more poses captured at different times and a consistent body shape is computed for all poses. The body may appear in minimal tight-fitting clothing or in normal clothing wherein the described method produces an estimate of the body shape under the clothing. Clothed or bare regions of the body are detected via image classification and the fitting method is adapted to treat each region differently. Body shapes are represented parametrically and are matched to other bodies based on shape similarity and other features. Standard measurements are extracted using parametric or non-parametric functions of body shape. The system components support many applications in body scanning, advertising, social networking, collaborative filtering and Internet clothing shopping.Type: GrantFiled: June 14, 2018Date of Patent: July 2, 2019Assignee: BROWN UNIVERSITYInventors: Michael J. Black, Alexandru O. Balan, Alexander W. Weiss, Leonid Sigal, Matthew M. Loper, Timothy S. St. Clair
-
Publication number: 20180293788Abstract: A system and method of estimating the body shape of an individual from input data such as images or range maps. The body may appear in one or more poses captured at different times and a consistent body shape is computed for all poses. The body may appear in minimal tight-fitting clothing or in normal clothing wherein the described method produces an estimate of the body shape under the clothing. Clothed or bare regions of the body are detected via image classification and the fitting method is adapted to treat each region differently. Body shapes are represented parametrically and are matched to other bodies based on shape similarity and other features. Standard measurements are extracted using parametric or non-parametric functions of body shape. The system components support many applications in body scanning, advertising, social networking, collaborative filtering and Internet clothing shopping.Type: ApplicationFiled: June 14, 2018Publication date: October 11, 2018Inventors: Michael J. BLACK, Alexandru O. BALAN, Alexander W. Weiss, Leonid SIGAL, Matthew M. LOPER, Timothy S. ST. CLAIR
-
Patent number: 10002460Abstract: A system and method of estimating the body shape of an individual from input data such as images or range maps. The body may appear in one or more poses captured at different times and a consistent body shape is computed for all poses. The body may appear in minimal tight-fitting clothing or in normal clothing wherein the described method produces an estimate of the body shape under the clothing. Clothed or bare regions of the body are detected via image classification and the fitting method is adapted to treat each region differently. Body shapes are represented parametrically and are matched to other bodies based on shape similarity and other features. Standard measurements are extracted using parametric or non-parametric functions of body shape. The system components support many applications in body scanning, advertising, social networking, collaborative filtering and Internet clothing shopping.Type: GrantFiled: October 16, 2015Date of Patent: June 19, 2018Assignee: BROWN UNIVERSITYInventors: Michael J. Black, Alexandru O. Balan, Alexander W. Weiss, Leonid Sigal, Matthew M. Loper, Timothy S. St. Clair
-
Publication number: 20180122146Abstract: Disclosed are computer-readable devices, systems and methods for generating a model of a clothed body. The method includes generating a model of an unclothed human body, the model capturing a shape or a pose of the unclothed human body, determining two-dimensional contours associated with the model, and computing deformations by aligning a contour of a clothed human body with a contour of the unclothed human body. Based on the two-dimensional contours and the deformations, the method includes generating a first two-dimensional model of the unclothed human body, the first two-dimensional model factoring the deformations of the unclothed human body into one or more of a shape variation component, a viewpoint change, and a pose variation and learning an eigen-clothing model using principal component analysis applied to the deformations, wherein the eigen-clothing model classifies different types of clothing, to yield a second two-dimensional model of a clothed human body.Type: ApplicationFiled: September 11, 2017Publication date: May 3, 2018Inventors: Michael J. Black, Oren Freifeld, Alexander W. Weiss, Matthew M. Loper, Peng Guan
-
Patent number: 9761060Abstract: Disclosed are computer-readable devices, systems and methods for generating a model of a clothed body. The method includes generating a model of an unclothed human body, the model capturing a shape or a pose of the unclothed human body, determining two-dimensional contours associated with the model, and computing deformations by aligning a contour of a clothed human body with a contour of the unclothed human body. Based on the two-dimensional contours and the deformations, the method includes generating a first two-dimensional model of the unclothed human body, the first two-dimensional model factoring the deformations of the unclothed human body into one or more of a shape variation component, a viewpoint change, and a pose variation and learning an eigen-clothing model using principal component analysis applied to the deformations, wherein the eigen-clothing model classifies different types of clothing, to yield a second two-dimensional model of a clothed human body.Type: GrantFiled: November 3, 2016Date of Patent: September 12, 2017Assignee: Brown UniversityInventors: Michael J. Black, Oren Freifeld, Alexander W. Weiss, Matthew M. Loper, Peng Guan
-
Publication number: 20170069102Abstract: Disclosed are computer-readable devices, systems and methods for generating a model of a clothed body. The method includes generating a model of an unclothed human body, the model capturing a shape or a pose of the unclothed human body, determining two-dimensional contours associated with the model, and computing deformations by aligning a contour of a clothed human body with a contour of the unclothed human body. Based on the two-dimensional contours and the deformations, the method includes generating a first two-dimensional model of the unclothed human body, the first two-dimensional model factoring the deformations of the unclothed human body into one or more of a shape variation component, a viewpoint change, and a pose variation and learning an eigen-clothing model using principal component analysis applied to the deformations, wherein the eigen-clothing model classifies different types of clothing, to yield a second two-dimensional model of a clothed human body.Type: ApplicationFiled: November 3, 2016Publication date: March 9, 2017Inventors: Michael J. Black, Oren Freifeld, Alexander W. Weiss, Matthew M. Loper, Peng Guan
-
Patent number: 9489744Abstract: A novel “contour person” (CP) model of the human body is proposed that has the expressive power of a detailed 3D model and the computational benefits of a simple 2D part-based model. The CP model is learned from a 3D model of the human body that captures natural shape and pose variations; the projected contours of this model, along with their segmentation into parts forms the training set. The CP model factors deformations of the body into three components: shape variation, viewpoint change and pose variation. The CP model can be “dressed” with a low-dimensional clothing model, referred to as “dressed contour person” (DCP) model. The clothing is represented as a deformation from the underlying CP representation. This deformation is learned from training examples using principal component analysis to produce so-called eigen-clothing. The coefficients of the eigen-clothing can be used to recognize different categories of clothing on dressed people.Type: GrantFiled: February 12, 2016Date of Patent: November 8, 2016Assignee: Brown UniversityInventors: Michael J. Black, Oren Freifeld, Alexander W. Weiss, Matthew M. Loper, Peng Guan
-
Publication number: 20160275693Abstract: A novel “contour person” (CP) model of the human body is proposed that has the expressive power of a detailed 3D model and the computational benefits of a simple 2D part-based model. The CP model is learned from a 3D model of the human body that captures natural shape and pose variations; the projected contours of this model, along with their segmentation into parts forms the training set. The CP model factors deformations of the body into three components: shape variation, viewpoint change and pose variation. The CP model can be “dressed” with a low-dimensional clothing model, referred to as “dressed contour person” (DCP) model. The clothing is represented as a deformation from the underlying CP representation. This deformation is learned from training examples using principal component analysis to produce so-called eigen-clothing. The coefficients of the eigen-clothing can be used to recognize different categories of clothing on dressed people.Type: ApplicationFiled: February 12, 2016Publication date: September 22, 2016Inventors: Michael J. Black, Oren Freifeld, Alexander W. Weiss, Matthew M. Loper, Peng Guan
-
Publication number: 20160203361Abstract: A system and method of estimating the body shape of an individual from input data such as images or range maps. The body may appear in one or more poses captured at different times and a consistent body shape is computed for all poses. The body may appear in minimal tight-fitting clothing or in normal clothing wherein the described method produces an estimate of the body shape under the clothing. Clothed or bare regions of the body are detected via image classification and the fitting method is adapted to treat each region differently. Body shapes are represented parametrically and are matched to other bodies based on shape similarity and other features. Standard measurements are extracted using parametric or non-parametric functions of body shape. The system components support many applications in body scanning, advertising, social networking, collaborative filtering and Internet clothing shopping.Type: ApplicationFiled: October 16, 2015Publication date: July 14, 2016Inventors: Michael J. Black, Alexandru O. Balan, Alexander W. Weiss, Leonid Sigal, Matthew M. Loper, Timothy S. St. Clair
-
Patent number: 9292967Abstract: A novel “contour person” (CP) model of the human body is proposed that has the expressive power of a detailed 3D model and the computational benefits of a simple 20 part-based model. The CP model is learned from a 3D model of the human body that captures natural shape and pose variations. The CP model factors deformations of the body into three components: shape variation, viewpoint change and pose variation. The CP model can be “dressed” with a low-dimensional clothing model. The clothing is represented as a deformation from the underlying CP representation. This deformation is learned from training examples using principal component analysis to produce so-called eigen-clothing. The coefficients of the eigen-clothing can be used to recognize different categories of clothing on dressed people. The parameters of the estimated 20 body can be used to discriminatively predict 3D body shape using a learned mapping approach.Type: GrantFiled: June 8, 2011Date of Patent: March 22, 2016Assignee: Brown UniversityInventors: Michael J. Black, Oren Freifeld, Alexander W. Weiss, Matthew M. Loper, Peng Guan
-
Patent number: 9189886Abstract: A system and method of estimating the body shape of an individual from input data such as images or range maps. The body may appear in one or more poses captured at different times and a consistent body shape is computed for all poses. The body may appear in minimal tight-fitting clothing or in normal clothing wherein the described method produces an estimate of the body shape under the clothing. Clothed or bare regions of the body are detected via image classification and the fitting method is adapted to treat each region differently. Body shapes are represented parametrically and are matched to other bodies based on shape similarity and other features. Standard measurements are extracted using parametric or non-parametric functions of body shape. The system components support many applications in body scanning, advertising, social networking, collaborative filtering and Internet clothing shopping.Type: GrantFiled: August 14, 2009Date of Patent: November 17, 2015Assignee: Brown UniversityInventors: Michael J. Black, Alexandru O. Balan, Alexander W. Weiss, Leonid Sigal, Matthew M. Loper, Timothy S. St. Clair
-
Publication number: 20150273768Abstract: This disclosure relates to systems, apparatus, and methods for producing three-dimensional (3D) objects in a manner more rapidly and cost efficiently than heretofore achievable. A cylindrical coordinate CNC system (CCCNC system) according to embodiments of this disclosure works by using a rotation and a translation or multiple rotations. In one aspect, a CCCNC system includes a bed that rotates on a platen. The platen translates from side to side (e.g., theta and r-axis, respectively). The rotating bed and the platen define the workspace for producing the 3D objects. In another aspect, the CCCNC system includes a head that moves up and down (z-axis) while remaining static in all other axes of motion. In various embodiments, the CCCNC system uses the r, theta, and z-coordinate system to execute any job or command of which a traditional Cartesian CNC system is capable.Type: ApplicationFiled: March 27, 2015Publication date: October 1, 2015Inventors: Travis I. Wyatt, Alexander W. Weiss
-
Publication number: 20130249908Abstract: A novel “contour person” (CP) model of the human body is proposed that has the expressive power of a detailed 3D model and the computational benefits of a simple 20 part-based model. The CP model is learned from a 3D model of the human body that captures natural shape and pose variations. The CP model factors deformations of the body into three components: shape variation, viewpoint change and pose variation. The CP model can be “dressed” with a low-dimensional clothing model. The clothing is represented as a deformation from the underlying CP representation. This deformation is learned from training examples using principal component analysis to produce so-called eigen-clothing. The coefficients of the eigen-clothing can be used to recognize different categories of clothing on dressed people. The parameters of the estimated 20 body can be used to discriminatively predict 3D body shape using a learned mapping approach.Type: ApplicationFiled: June 8, 2011Publication date: September 26, 2013Inventors: Michael J. Black, Oren Freifeld, Alexander W. Weiss, Matthew M. Loper, Peng Guan