Patents by Inventor Morgan FABIAN

Morgan FABIAN 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: 11928773
    Abstract: In various embodiments, a training application generates a trained encoder that automatically generates shape embeddings having a first size and representing three-dimensional (3D) geometry shapes. First, the training application generates a different view activation for each of multiple views associated with a first 3D geometry based on a first convolutional neural network (CNN) block. The training application then aggregates the view activations to generate a tiled activation. Subsequently, the training application generates a first shape embedding having the first size based on the tiled activation and a second CNN block. The training application then generates multiple re-constructed views based on the first shape embedding. The training application performs training operation(s) on at least one of the first CNN block and the second CNN block based on the views and the re-constructed views to generate the trained encoder.
    Type: Grant
    Filed: February 23, 2022
    Date of Patent: March 12, 2024
    Assignee: AUTODESK, INC.
    Inventors: Thomas Ryan Davies, Michael Haley, Ara Danielyan, Morgan Fabian
  • Publication number: 20230343058
    Abstract: In various embodiments, a training application trains a machine learning model to modify portions of shapes when designing 3D objects. The training application converts first structural analysis data having a first resolution to first coarse structural analysis data having a second resolution that is lower than the first resolution. Subsequently, the training application generates one or more training sets based on a first shape, the first coarse structural analysis data, and a second shape that is derived from the first shape. Each training set is associated with a different portion of the first shape. The training application then performs one or more machine learning operations on the machine learning model using the training set(s) to generate a trained machine learning model. The trained machine learning model modifies at least a portion of a shape having the first resolution based on coarse structural analysis data having the second resolution.
    Type: Application
    Filed: July 3, 2023
    Publication date: October 26, 2023
    Inventors: Ran ZHANG, Morgan FABIAN, Ebot Etchu NDIP-AGBOR, Lee Morris TAYLOR
  • Patent number: 11741662
    Abstract: In various embodiments, a training application generates a trained encoder that automatically generates shape embeddings having a first size and representing three-dimensional (3D) geometry shapes. First, the training application generates a different view activation for each of multiple views associated with a first 3D geometry based on a first convolutional neural network (CNN) block. The training application then aggregates the view activations to generate a tiled activation. Subsequently, the training application generates a first shape embedding having the first size based on the tiled activation and a second CNN block. The training application then generates multiple re-constructed views based on the first shape embedding. The training application performs training operation(s) on at least one of the first CNN block and the second CNN block based on the views and the re-constructed views to generate the trained encoder.
    Type: Grant
    Filed: October 29, 2018
    Date of Patent: August 29, 2023
    Assignee: AUTODESK, INC.
    Inventors: Thomas Davies, Michael Haley, Ara Danielyan, Morgan Fabian
  • Patent number: 11694415
    Abstract: In various embodiments, a training application trains a machine learning model to modify portions of shapes when designing 3D objects. The training application converts first structural analysis data having a first resolution to first coarse structural analysis data having a second resolution that is lower than the first resolution. Subsequently, the training application generates one or more training sets based on a first shape, the first coarse structural analysis data, and a second shape that is derived from the first shape. Each training set is associated with a different portion of the first shape. The training application then performs one or more machine learning operations on the machine learning model using the training set(s) to generate a trained machine learning model. The trained machine learning model modifies at least a portion of a shape having the first resolution based on coarse structural analysis data having the second resolution.
    Type: Grant
    Filed: October 28, 2020
    Date of Patent: July 4, 2023
    Assignee: AUTODESK, INC.
    Inventors: Ran Zhang, Morgan Fabian, Ebot Etchu Ndip-Agbor, Lee Morris Taylor
  • Patent number: 11468634
    Abstract: In various embodiments, a topology optimization application solves a topology optimization problem associated with designing a three-dimensional (ā€œ3Dā€) object. The topology optimization application coverts a first shape having a first resolution and representing the 3D object to a coarse shape having a second resolution that is lower than the first resolution. Subsequently, the topology optimization application computes coarse structural analysis data based on the coarse shape. The topology optimization application then uses a trained machine learning model to generate a second shape having the first resolution and representing the 3D object based on the first shape and the coarse structural analysis data. The trained machine learning model modifies a portion of a shape having the first resolution based on structural analysis data having the second resolution.
    Type: Grant
    Filed: October 28, 2020
    Date of Patent: October 11, 2022
    Assignee: AUTODESK, INC.
    Inventors: Ran Zhang, Morgan Fabian, Ebot Ndip-Agbor, Lee Morris Taylor
  • Patent number: 11380045
    Abstract: In various embodiments, a training application generates a trained encoder that automatically generates shape embeddings having a first size and representing three-dimensional (3D) geometry shapes. First, the training application generates a different view activation for each of multiple views associated with a first 3D geometry based on a first convolutional neural network (CNN) block. The training application then aggregates the view activations to generate a tiled activation. Subsequently, the training application generates a first shape embedding having the first size based on the tiled activation and a second CNN block. The training application then generates multiple re-constructed views based on the first shape embedding. The training application performs training operation(s) on at least one of the first CNN block and the second CNN block based on the views and the re-constructed views to generate the trained encoder.
    Type: Grant
    Filed: October 29, 2018
    Date of Patent: July 5, 2022
    Assignee: AUTODESK, INC.
    Inventors: Thomas Davies, Michael Haley, Ara Danielyan, Morgan Fabian
  • Publication number: 20220180596
    Abstract: In various embodiments, a training application generates a trained encoder that automatically generates shape embeddings having a first size and representing three-dimensional (3D) geometry shapes. First, the training application generates a different view activation for each of multiple views associated with a first 3D geometry based on a first convolutional neural network (CNN) block. The training application then aggregates the view activations to generate a tiled activation. Subsequently, the training application generates a first shape embedding having the first size based on the tiled activation and a second CNN block. The training application then generates multiple re-constructed views based on the first shape embedding. The training application performs training operation(s) on at least one of the first CNN block and the second CNN block based on the views and the re-constructed views to generate the trained encoder.
    Type: Application
    Filed: February 23, 2022
    Publication date: June 9, 2022
    Inventors: Thomas Ryan DAVIES, Michael HALEY, Ara DANIELYAN, Morgan FABIAN
  • Publication number: 20220130110
    Abstract: In various embodiments, a topology optimization application solves a topology optimization problem associated with designing a three-dimensional (ā€œ3Dā€) object. The topology optimization application coverts a first shape having a first resolution and representing the 3D object to a coarse shape having a second resolution that is lower than the first resolution. Subsequently, the topology optimization application computes coarse structural analysis data based on the coarse shape. The topology optimization application then uses a trained machine learning model to generate a second shape having the first resolution and representing the 3D object based on the first shape and the coarse structural analysis data. The trained machine learning model modifies a portion of a shape having the first resolution based on structural analysis data having the second resolution.
    Type: Application
    Filed: October 28, 2020
    Publication date: April 28, 2022
    Inventors: Ran ZHANG, Morgan FABIAN, Ebot NDIP-AGBOR, Lee Morris TAYLOR
  • Publication number: 20220130127
    Abstract: In various embodiments, a training application trains a machine learning model to modify portions of shapes when designing 3D objects. The training application converts first structural analysis data having a first resolution to first coarse structural analysis data having a second resolution that is lower than the first resolution. Subsequently, the training application generates one or more training sets based on a first shape, the first coarse structural analysis data, and a second shape that is derived from the first shape. Each training set is associated with a different portion of the first shape. The training application then performs one or more machine learning operations on the machine learning model using the training set(s) to generate a trained machine learning model. The trained machine learning model modifies at least a portion of a shape having the first resolution based on coarse structural analysis data having the second resolution.
    Type: Application
    Filed: October 28, 2020
    Publication date: April 28, 2022
    Inventors: Ran ZHANG, Morgan FABIAN, Ebot NDIP-AGBOR, Lee Morris TAYLOR
  • Patent number: 11126330
    Abstract: In various embodiments, a training application generates a trained encoder that automatically generates shape embeddings having a first size and representing three-dimensional (3D) geometry shapes, First, the training application generates a different view activation for each of multiple views associated with a first 3D geometry based on a first convolutional neural network (CNN) block. The training application then aggregates the view activations to generate a tiled activation. Subsequently, the training application generates a first shape embedding having the first size based on the tiled activation and a second CNN block. The training application then generates multiple re-constructed views based on the first shape embedding. The training application performs training operation(s) on at least one of the first CNN block and the second CNN block based on the views and the re-constructed views to generate the trained encoder.
    Type: Grant
    Filed: October 29, 2018
    Date of Patent: September 21, 2021
    Assignee: AUTODESK, INC.
    Inventors: Thomas Davies, Michael Haley, Ara Danielyan, Morgan Fabian
  • Publication number: 20200133449
    Abstract: In various embodiments, a training application generates a trained encoder that automatically generates shape embeddings having a first size and representing three-dimensional (3D) geometry shapes, First, the training application generates a different view activation for each of multiple views associated with a first 3D geometry based on a first convolutional neural network (CNN) block. The training application then aggregates the view activations to generate a tiled activation. Subsequently, the training application generates a first shape embedding having the first size based on the tiled activation and a second CNN block. The training application then generates multiple re-constructed views based on the first shape embedding. The training application performs training operation(s) on at least one of the first CNN block and the second CNN block based on the views and the re-constructed views to generate the trained encoder.
    Type: Application
    Filed: October 29, 2018
    Publication date: April 30, 2020
    Inventors: Thomas DAVIES, Michael HALEY, Ara DANIELYAN, Morgan FABIAN
  • Publication number: 20200134909
    Abstract: In various embodiments, a training application generates a trained encoder that automatically generates shape embeddings having a first size and representing three-dimensional (3D) geometry shapes. First, the training application generates a different view activation for each of multiple views associated with a first 3D geometry based on a first convolutional neural network (CNN) block. The training application then aggregates the view activations to generate a tiled activation. Subsequently, the training application generates a first shape embedding having the first size based on the tiled activation and a second CNN block. The training application then generates multiple re-constructed views based on the first shape embedding. The training application performs training operation(s) on at least one of the first CNN block and the second CNN block based on the views and the re-constructed views to generate the trained encoder.
    Type: Application
    Filed: October 29, 2018
    Publication date: April 30, 2020
    Inventors: Thomas DAVIES, Michael HALEY, Ara DANIELYAN, Morgan FABIAN
  • Publication number: 20200134908
    Abstract: In various embodiments, a training application generates a trained encoder that automatically generates shape embeddings having a first size and representing three-dimensional (3D) geometry shapes. First, the training application generates a different view activation for each of multiple views associated with a first 3D geometry based on a first convolutional neural network (CNN) block. The training application then aggregates the view activations to generate a tiled activation. Subsequently, the training application generates a first shape embedding having the first size based on the tiled activation and a second CNN block. The training application then generates multiple re-constructed views based on the first shape embedding. The training application performs training operation(s) on at least one of the first CNN block and the second CNN block based on the views and the re-constructed views to generate the trained encoder.
    Type: Application
    Filed: October 29, 2018
    Publication date: April 30, 2020
    Inventors: Thomas DAVIES, Michael HALEY, Ara DANIELYAN, Morgan FABIAN