Patents by Inventor Aaron Phillip Hertzmann

Aaron Phillip Hertzmann 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: 11050994
    Abstract: Virtual reality parallax correction techniques and systems are described that are configured to correct parallax for VR digital content captured from a single point of origin. In one example, a parallax correction module is employed to correct artifacts caused in a change from a point of origin that corresponds to the VR digital content to a new viewpoint with respect to an output of the VR digital content. A variety of techniques may be employed by the parallax correction module to correct parallax. Examples of these techniques include depth filtering, boundary identification, smear detection, mesh cutting, confidence estimation, blurring, and error diffusion as further described in the following sections.
    Type: Grant
    Filed: June 3, 2020
    Date of Patent: June 29, 2021
    Assignee: Adobe Inc.
    Inventors: Stephen Joseph DiVerdi, Ana Belén Serrano Pacheu, Aaron Phillip Hertzmann
  • Patent number: 11003831
    Abstract: The present disclosure relates to an asymmetric font pairing system that efficiently pairs digital fonts. For example, in one or more embodiments, the asymmetric font pairing system automatically identifies and provides users with visually aesthetic font pairs for use in different sections of an electronic document. In particular, the asymmetric font pairing system learns visually aesthetic font pairs using joint symmetric and asymmetric compatibility metric learning. In addition, the asymmetric font pairing system provides compact compatibility spaces (e.g., a symmetric compatibility space and an asymmetric compatibility space) to computing devices (e.g., client devices and server devices), which enable the computing devices to quickly and efficiently provide font pairs to users.
    Type: Grant
    Filed: October 11, 2017
    Date of Patent: May 11, 2021
    Assignee: ADOBE INC.
    Inventors: Zhaowen Wang, Hailin Jin, Aaron Phillip Hertzmann, Shuhui Jiang
  • Patent number: 10997464
    Abstract: Digital image layout training is described using wireframe rendering within a generative adversarial network (GAN) system. A GAN system is employed to train the generator module to refine digital image layouts. To do so, a wireframe rendering discriminator module rasterizes a refined digital training digital image layout received from a generator module into a wireframe digital image layout. The wireframe digital image layout is then compared with at least one ground truth digital image layout using a loss function as part of machine learning by the wireframe discriminator module. The generator module is then trained by backpropagating a result of the comparison.
    Type: Grant
    Filed: November 9, 2018
    Date of Patent: May 4, 2021
    Assignee: Adobe Inc.
    Inventors: Jimei Yang, Jianming Zhang, Aaron Phillip Hertzmann, Jianan Li
  • Patent number: 10803642
    Abstract: Techniques and systems to support collaborative interaction as part of virtual reality video are described. In one example, a viewport is generated such that a reviewing user of a reviewing user device may view VR video viewed by a source user of a source user device. The viewport, for instance, may be configured as a border at least partially surrounding a portion of the VR video output by the reviewing VR device. In another instance, the viewport is configured to support output of thumbnails within an output of VR video by the reviewing VR device. Techniques and systems are also described to support communication of annotations between the source and reviewing VR devices. Techniques and systems are also described to support efficient distribution of VR video within a context of a content editing application.
    Type: Grant
    Filed: August 18, 2017
    Date of Patent: October 13, 2020
    Assignee: Adobe Inc.
    Inventors: Stephen Joseph DiVerdi, Aaron Phillip Hertzmann, Brian David Williams
  • Publication number: 20200296348
    Abstract: Virtual reality parallax correction techniques and systems are described that are configured to correct parallax for VR digital content captured from a single point of origin. In one example, a parallax correction module is employed to correct artifacts caused in a change from a point of origin that corresponds to the VR digital content to a new viewpoint with respect to an output of the VR digital content. A variety of techniques may be employed by the parallax correction module to correct parallax. Examples of these techniques include depth filtering, boundary identification, smear detection, mesh cutting, confidence estimation, blurring, and error diffusion as further described in the following sections.
    Type: Application
    Filed: June 3, 2020
    Publication date: September 17, 2020
    Applicant: Adobe Inc.
    Inventors: Stephen Joseph DiVerdi, Ana Belén Serrano Pacheu, Aaron Phillip Hertzmann
  • Patent number: 10701334
    Abstract: Virtual reality parallax correction techniques and systems are described that are configured to correct parallax for VR digital content captured from a single point of origin. In one example, a parallax correction module is employed to correct artifacts caused in a change from a point of origin that corresponds to the VR digital content to a new viewpoint with respect to an output of the VR digital content. A variety of techniques may be employed by the parallax correction module to correct parallax. Examples of these techniques include depth filtering, boundary identification, smear detection, mesh cutting, confidence estimation, blurring, and error diffusion as further described in the following sections.
    Type: Grant
    Filed: October 11, 2017
    Date of Patent: June 30, 2020
    Assignee: Adobe Inc.
    Inventors: Stephen Joseph DiVerdi, Ana Belén Serrano Pacheu, Aaron Phillip Hertzmann
  • Publication number: 20200151508
    Abstract: Digital image layout training is described using wireframe rendering within a generative adversarial network (GAN) system. A GAN system is employed to train the generator module to refine digital image layouts. To do so, a wireframe rendering discriminator module rasterizes a refined digital training digital image layout received from a generator module into a wireframe digital image layout. The wireframe digital image layout is then compared with at least one ground truth digital image layout using a loss function as part of machine learning by the wireframe discriminator module. The generator module is then trained by backpropagating a result of the comparison.
    Type: Application
    Filed: November 9, 2018
    Publication date: May 14, 2020
    Applicant: Adobe Inc.
    Inventors: Jimei Yang, Jianming Zhang, Aaron Phillip Hertzmann, Jianan Li
  • Patent number: 10613703
    Abstract: Techniques and systems to support collaborative interaction as part of virtual reality video are described. In one example, a viewport is generated such that a reviewing user of a reviewing user device may view VR video viewed by a source user of a source user device. The viewport, for instance, may be configured as a border at least partially surrounding a portion of the VR video output by the reviewing VR device. In another instance, the viewport is configured to support output of thumbnails within an output of VR video by the reviewing VR device. Techniques and systems are also described to support communication of annotations between the source and reviewing VR devices. Techniques and systems are also described to support efficient distribution of VR video within a context of a content editing application.
    Type: Grant
    Filed: August 18, 2017
    Date of Patent: April 7, 2020
    Assignee: Adobe Inc.
    Inventors: Stephen Joseph DiVerdi, Aaron Phillip Hertzmann, Cuong D. Nguyen
  • Publication number: 20190110038
    Abstract: Virtual reality parallax correction techniques and systems are described that are configured to correct parallax for VR digital content captured from a single point of origin. In one example, a parallax correction module is employed to correct artifacts caused in a change from a point of origin that corresponds to the VR digital content to a new viewpoint with respect to an output of the VR digital content. A variety of techniques may be employed by the parallax correction module to correct parallax. Examples of these techniques include depth filtering, boundary identification, smear detection, mesh cutting, confidence estimation, blurring, and error diffusion as further described in the following sections.
    Type: Application
    Filed: October 11, 2017
    Publication date: April 11, 2019
    Applicant: Adobe Systems Incorporated
    Inventors: Stephen Joseph DiVerdi, Ana Belén Serrano Pacheu, Aaron Phillip Hertzmann
  • Publication number: 20190108203
    Abstract: The present disclosure relates to an asymmetric font pairing system that efficiently pairs digital fonts. For example, in one or more embodiments, the asymmetric font pairing system automatically identifies and provides users with visually aesthetic font pairs for use in different sections of an electronic document. In particular, the asymmetric font pairing system learns visually aesthetic font pairs using joint symmetric and asymmetric compatibility metric learning. In addition, the asymmetric font pairing system provides compact compatibility spaces (e.g., a symmetric compatibility space and an asymmetric compatibility space) to computing devices (e.g., client devices and server devices), which enable the computing devices to quickly and efficiently provide font pairs to users.
    Type: Application
    Filed: October 11, 2017
    Publication date: April 11, 2019
    Inventors: Zhaowen Wang, Hailin Jin, Aaron Phillip Hertzmann, Shuhui Jiang
  • Patent number: 10235897
    Abstract: Methods for providing drawing assistance to a user sketching an image include geometrically correcting adjusting user strokes to improve their placement and appearance. In particular, one or more guidance maps indicate where the user “should” draw lines. As a user draws a stroke, the stroke is geometrically corrected by moving the stroke toward a portion of the guidance maps corresponding to the feature of the image the user is intending to draw based feature labels. To further improve the user drawn lines, parametric adjustments are optionally made to the geometrically-corrected stroke to emphasize “correctly” drawn lines and de-emphasize “incorrectly” drawn lines.
    Type: Grant
    Filed: October 14, 2016
    Date of Patent: March 19, 2019
    Assignee: ADOBE INC.
    Inventors: Holger Winnemoeller, Jun Xie, Wilmot Wei-Mau Li, Aaron Phillip Hertzmann
  • Publication number: 20190056848
    Abstract: Techniques and systems to support collaborative interaction as part of virtual reality video are described. In one example, a viewport is generated such that a reviewing user of a reviewing user device may view VR video viewed by a source user of a source user device. The viewport, for instance, may be configured as a border at least partially surrounding a portion of the VR video output by the reviewing VR device. In another instance, the viewport is configured to support output of thumbnails within an output of VR video by the reviewing VR device. Techniques and systems are also described to support communication of annotations between the source and reviewing VR devices. Techniques and systems are also described to support efficient distribution of VR video within a context of a content editing application.
    Type: Application
    Filed: August 18, 2017
    Publication date: February 21, 2019
    Applicant: Adobe Systems Incorporated
    Inventors: Stephen Joseph DiVerdi, Aaron Phillip Hertzmann, Cuong D. Nguyen
  • Publication number: 20190057529
    Abstract: Techniques and systems to support collaborative interaction as part of virtual reality video are described. In one example, a viewport is generated such that a reviewing user of a reviewing user device may view VR video viewed by a source user of a source user device. The viewport, for instance, may be configured as a border at least partially surrounding a portion of the VR video output by the reviewing VR device. In another instance, the viewport is configured to support output of thumbnails within an output of VR video by the reviewing VR device. Techniques and systems are also described to support communication of annotations between the source and reviewing VR devices. Techniques and systems are also described to support efficient distribution of VR video within a context of a content editing application.
    Type: Application
    Filed: August 18, 2017
    Publication date: February 21, 2019
    Applicant: Adobe Systems Incorporated
    Inventors: Stephen Joseph DiVerdi, Aaron Phillip Hertzmann, Brian David Williams
  • Patent number: 9972107
    Abstract: Embodiments of the present invention provide systems, methods, and computer storage media directed at decomposing a graphic design into constituent parts. In embodiments, a decomposition module is configured to partition pixels of a graphic design image into superpixels. This partitioning can be based on a color analysis of individual pixels of the graphic design image. Once partitioned into superpixels, the decomposition module may group the superpixels into components such that each component includes superpixels that are within a level of similarity from one another. The decomposition module can then categorize one or more of the components as textual elements of the graphic design based on text identification features of the components. Other embodiments may be described and/or claimed herein.
    Type: Grant
    Filed: May 29, 2015
    Date of Patent: May 15, 2018
    Assignee: Adobe Systems Incorporated
    Inventors: Aseem Agarwala, Mohammad Amin Sadeghi, Aaron Phillip Hertzmann
  • Publication number: 20170032690
    Abstract: Methods for providing drawing assistance to a user sketching an image include geometrically correcting adjusting user strokes to improve their placement and appearance. In particular, one or more guidance maps indicate where the user “should” draw lines. As a user draws a stroke, the stroke is geometrically corrected by moving the stroke toward a portion of the guidance maps corresponding to the feature of the image the user is intending to draw based feature labels. To further improve the user drawn lines, parametric adjustments are optionally made to the geometrically-corrected stroke to emphasize “correctly” drawn lines and de-emphasize “incorrectly” drawn lines.
    Type: Application
    Filed: October 14, 2016
    Publication date: February 2, 2017
    Inventors: Holger Winnemoeller, Jun Xie, Wilmot Wei-Mau Li, Aaron Phillip Hertzmann
  • Publication number: 20160350954
    Abstract: Embodiments of the present invention provide systems, methods, and computer storage media directed at decomposing a graphic design into constituent parts. In embodiments, a decomposition module is configured to partition pixels of a graphic design image into superpixels. This partitioning can be based on a color analysis of individual pixels of the graphic design image. Once partitioned into superpixels, the decomposition module may group the superpixels into components such that each component includes superpixels that are within a level of similarity from one another. The decomposition module can then categorize one or more of the components as textual elements of the graphic design based on text identification features of the components. Other embodiments may be described and/or claimed herein.
    Type: Application
    Filed: May 29, 2015
    Publication date: December 1, 2016
    Inventors: ASEEM AGARWALA, MOHAMMAD AMIN SADEGHI, AARON PHILLIP HERTZMANN
  • Patent number: 9495581
    Abstract: Methods for providing drawing assistance to a user sketching an image include geometrically correcting adjusting user strokes to improve their placement and appearance. In particular, one or more guidance maps indicate where the user “should” draw lines. As a user draws a stroke, the stroke is geometrically corrected by moving the stroke toward a portion of the guidance maps corresponding to the feature of the image the user is intending to draw based feature labels. To further improve the user drawn lines, parametric adjustments are optionally made to the geometrically-corrected stroke to emphasize “correctly” drawn lines and de-emphasize “incorrectly” drawn lines.
    Type: Grant
    Filed: February 7, 2014
    Date of Patent: November 15, 2016
    Assignee: ADOBE SYSTEMS INCORPORATED
    Inventors: Holger Winnemoeller, Jun Xie, Wilmot Wei-Mau Li, Aaron Phillip Hertzmann
  • Patent number: 9305382
    Abstract: Methods for providing drawing assistance to a user sketching an image include geometrically correcting and parametrically adjusting user strokes to improve their placement and appearance. As a user draws a stroke, the stroke is geometrically corrected by moving the stroke toward a feature of the image the user is intending to draw. To further improve the user strokes, parametric adjustments are made to the geometrically-corrected stroke to emphasize “correctly” drawn lines and de-emphasize “incorrectly” drawn lines.
    Type: Grant
    Filed: February 3, 2014
    Date of Patent: April 5, 2016
    Assignee: ADOBE SYSTEMS INCORPORATED
    Inventors: Holger Winnemoeller, Jun Xie, Wilmot Wei-Mau Li, Aaron Phillip Hertzmann
  • Publication number: 20150221106
    Abstract: Methods for providing drawing assistance to a user sketching an image include geometrically correcting and parametrically adjusting user strokes to improve their placement and appearance. As a user draws a stroke, the stroke is geometrically corrected by moving the stroke toward a feature of the image the user is intending to draw. To further improve the user strokes, parametric adjustments are made to the geometrically-corrected stroke to emphasize “correctly” drawn lines and de-emphasize “incorrectly” drawn lines.
    Type: Application
    Filed: February 3, 2014
    Publication date: August 6, 2015
    Applicant: Adobe Systems Incorporated
    Inventors: Holger Winnemoeller, Jun Xie, Wilmot Wei-Mau Li, Aaron Phillip Hertzmann
  • Publication number: 20150221070
    Abstract: Methods for providing drawing assistance to a user sketching an image include geometrically correcting adjusting user strokes to improve their placement and appearance. In particular, one or more guidance maps indicate where the user “should” draw lines. As a user draws a stroke, the stroke is geometrically corrected by moving the stroke toward a portion of the guidance maps corresponding to the feature of the image the user is intending to draw based feature labels. To further improve the user drawn lines, parametric adjustments are optionally made to the geometrically-corrected stroke to emphasize “correctly” drawn lines and de-emphasize “incorrectly” drawn lines.
    Type: Application
    Filed: February 7, 2014
    Publication date: August 6, 2015
    Applicant: Adobe Systems Incorporated
    Inventors: Holger Winnemoeller, Jun Xie, Wilmot Wei-Mau Li, Aaron Phillip Hertzmann