公开(公告)号：US20250131677A1

公开(公告)日：2025-04-24

申请号：US19005926

申请日：2024-12-30

Applicant: AUTODESK, INC.

Inventor： Hooman SHAYANI ,  Marco FUMERO ,  Aditya SANGHI

IPC: G06T19/20 ,  G06N3/0455 ,  G06N3/0475 ,  G06N3/08 ,  G06N3/092 ,  G06T17/00 ,  G06T17/10

Abstract: One embodiment of the present invention sets forth a technique for training a machine learning model to perform style transfer. The technique includes applying one or more augmentations to a first input three-dimensional (3D) shape to generate a second input 3D shape. The technique also includes generating, via a first set of neural network layers, a style code based on a first latent representation of the first input 3D shape and a second latent representation of the second input 3D shape. The technique further includes generating, via a second set of neural network layers, a first output 3D shape based on the style code and the second latent representation, and performing one or more operations on the first and second sets of neural network layers based on a first loss associated with the first output 3D shape to generate a trained machine learning model.

公开(公告)号：US20240289502A1

公开(公告)日：2024-08-29

申请号：US18407320

申请日：2024-01-08

Applicant: AUTODESK, INC.

Inventor： Pradeep Kumar JAYARAMAN ,  Nishkrit DESAI ,  Joseph George LAMBOURNE ,  Nigel Jed Wesley MORRIS ,  Aditya SANGHI ,  Karl D. D. WILLIS

IPC: G06F30/10

CPC classification number: G06F30/10

Abstract: One embodiment of the present invention sets forth a technique for generating 3D CAD model representations of three-dimensional objects in boundary representation format. The technique includes generating an indexed boundary representation of the generated 3D CAD model. The indexed boundary representation includes ordered lists of vertices, edges, and faces defining the generated 3D CAD model, where the edges are encoded as references to vertices in the vertex list and the face are encoded as references to edges in the edge list. The technique further includes converting the indexed boundary representation of the generated 3D CAD model into a boundary representation of the 3D CAD model through the application of heuristic algorithms to the indexed boundary representation. The technique is optionally guided by conditional data associated with the 3D CAD model to be generated, including a 2D image, a 3D collection of volume elements, or a 3D point cloud.

公开(公告)号：US20240289505A1

公开(公告)日：2024-08-29

申请号：US18407327

申请日：2024-01-08

Applicant: AUTODESK, INC.

Inventor： Pradeep Kumar JAYARAMAN ,  Nishkrit DESAI ,  Joseph George LAMBOURNE ,  Nigel Jed Wesley MORRIS ,  Aditya SANGHI ,  Karl D. D. WILLIS

IPC: G06F30/12 ,  G06N7/01

CPC classification number: G06F30/12 ,  G06N7/01

Abstract: One embodiment of the present invention sets forth a technique for generating 3D CAD model representations of three-dimensional objects. The technique includes generating a vertex list that includes a first ordered list of elements representing vertex coordinates and sampling a first index from the vertex list based on a first probability distribution. The technique also includes generating an edge list and sampling a second index from one or more indices into the edge list. The technique further includes generating an element in a face list, dereferencing the element in the face list to retrieve an element in the edge list, and dereferencing an element in the edge list to retrieve a vertex coordinate from an element in the vertex list. The technique further includes generating an indexed boundary representation for the 3D CAD model based on at least the vertex list, the edge list, and the face list.

公开(公告)号：US20230326158A1

公开(公告)日：2023-10-12

申请号：US18149605

申请日：2023-01-03

Applicant: AUTODESK, INC.

Inventor： Hooman SHAYANI ,  Marco FUMERO ,  Aditya SANGHI

IPC: G06T19/20 ,  G06N3/0475 ,  G06N3/092

CPC classification number: G06T19/20 ,  G06N3/0475 ,  G06T2219/2024 ,  G06T2219/2021 ,  G06N3/092

Abstract: One embodiment of the present invention sets forth a technique for training a machine learning model to perform style transfer. The technique includes applying one or more augmentations to a first input three-dimensional (3D) shape to generate a second input 3D shape. The technique also includes generating, via a first set of neural network layers, a style code based on a first latent representation of the first input 3D shape and a second latent representation of the second input 3D shape. The technique further includes generating, via a second set of neural network layers, a first output 3D shape based on the style code and the second latent representation, and performing one or more operations on the first and second sets of neural network layers based on a first loss associated with the first output 3D shape to generate a trained machine learning model.

公开(公告)号：US20220156420A1

公开(公告)日：2022-05-19

申请号：US17523749

申请日：2021-11-10

Applicant: AUTODESK, INC.

Inventor： Peter MELTZER ,  Amir Hosein KHAS AHMADI ,  Pradeep Kumar JAYARAMAN ,  Joseph George LAMBOURNE ,  Aditya SANGHI ,  Hooman SHAYANI

IPC: G06F30/12 ,  G06F30/27

Abstract: In various embodiments, a style comparison application generates visualization(s) of geometric style gradient(s). The style comparison application generates a first set of style signals based on a first 3D CAD object and generates a second set of style signals based on a second 3D CAD object. Based on the first and second sets of style signals, the style comparison application computes a different partial derivative of a style comparison metric for each position included in a set of positions associated with the first 3D CAD object to generate a geometric style gradient. The style comparison application generates a graphical element based on at least one of the direction or the magnitude of a vector in the geometric style gradient and positions the graphical element relative to a graphical representation of the first 3D CAD object within a graphical user interface to generate a visualization of the geometric style gradient.

公开(公告)号：US20240331282A1

公开(公告)日：2024-10-03

申请号：US18488383

申请日：2023-10-17

Applicant: AUTODESK, INC.

Inventor： Evan Patrick ATHERTON ,  Saeid ASGARI TAGHANAKI ,  Pradeep Kumar JAYARAMAN ,  Joseph George LAMBOURNE ,  Arianna RAMPINI ,  Aditya SANGHI ,  Hooman SHAYANI

IPC: G06T17/00 ,  G06T11/20 ,  G06V10/44

CPC classification number: G06T17/00 ,  G06T11/203 ,  G06V10/44

Abstract: One embodiment of the present invention sets forth a technique for performing 3D shape generation. This technique includes generating semantic features associated with an input sketch. The technique also includes generating, using a generative machine learning model, a plurality of predicted shape embeddings from a set of fully masked shape embeddings based on the semantic features associated with the input sketch. The technique further includes converting the predicted shape embeddings into one or more 3D shapes. The input sketch may be a casual doodle, a professional illustration, or a 2D CAD software rendering. Each of the one or more 3D shapes may be a voxel representation, an implicit representation, or a 3D CAD software representation.

公开(公告)号：US20230326157A1

公开(公告)日：2023-10-12

申请号：US18149601

申请日：2023-01-03

Applicant: AUTODESK, INC.

Inventor： Hooman SHAYANI ,  Marco FUMERO ,  Aditya SANGHI

IPC: G06T19/20 ,  G06T17/10

CPC classification number: G06T19/20 ,  G06T17/10 ,  G06T2219/2024

Abstract: One embodiment of the present invention sets forth a technique for performing style transfer. The technique includes generating an input shape representation that includes a plurality of points near a surface of an input three-dimensional (3D) shape, where the input 3D shape includes content-based attributes associated with an object. The technique also includes determining a style code based on a difference between a first latent representation of a first 3D shape and a second latent representation of a second 3D shape, where the second 3D shape is generated by applying one or more augmentations to the first 3D shape. The technique further includes generating, based on the input shape representation and style code, an output 3D shape having the content-based attributes of the input 3D shape and style-based attributes associated with the style code, and generating a 3D model of the object based on the output 3D shape.

公开(公告)号：US20220318636A1

公开(公告)日：2022-10-06

申请号：US17348314

申请日：2021-06-15

Applicant: AUTODESK, INC.

Inventor： Pradeep Kumar JAYARAMAN ,  Thomas Ryan DAVIES ,  Joseph George LAMBOURNE ,  Nigel Jed Wesley MORRIS ,  Aditya SANGHI ,  Hooman SHAYANI

IPC: G06N3/08 ,  G06N3/04 ,  G06F30/10 ,  G06F16/901

Abstract: In various embodiments, a training application trains machine learning models to perform tasks associated with 3D CAD objects that are represented using B-reps. In operation, the training application computes a preliminary result via a machine learning model based on a representation of a 3D CAD object that includes a graph and multiple 2D UV-grids. Based on the preliminary result, the training application performs one or more operations to determine that the machine learning model has not been trained to perform a first task. The training application updates at least one parameter of a graph neural network included in the machine learning model based on the preliminary result to generate a modified machine learning model. The training application performs one or more operations to determine that the modified machine learning model has been trained to perform the first task.

公开(公告)号：US20220318637A1

公开(公告)日：2022-10-06

申请号：US17348338

申请日：2021-06-15

Applicant: AUTODESK, INC.

Inventor： Pradeep Kumar JAYARAMAN ,  Thomas Ryan DAVIES ,  Joseph George LAMBOURNE ,  Nigel Jed Wesley MORRIS ,  Aditya SANGHI ,  Hooman SHAYANI

IPC: G06N3/08 ,  G06N3/04 ,  G06F30/10 ,  G06F16/901

Abstract: In various embodiments, an inference application performs tasks associated with 3D CAD objects that are represented using B-reps. A UV-net representation of a 3D CAD object that is represented using a B-rep includes a set of 2D UV-grids and a graph. In operation, the inference application maps the set of 2D UV-grids to a set of node feature vectors via a trained neural network. Based on the node feature vectors and the graph, the inference application computes a final result via a trained graph neural network. Advantageously, the UV-net representation of the 3D CAD object enabled the trained neural network and the trained graph neural network to efficiently process the 3D CAD object.

公开(公告)号：US20220318466A1

公开(公告)日：2022-10-06

申请号：US17348295

申请日：2021-06-15

Applicant: AUTODESK, INC.

Inventor： Pradeep Kumar JAYARAMAN ,  Thomas Ryan DAVIES ,  Joseph George LAMBOURNE ,  Nigel Jed Wesley MORRIS ,  Aditya SANGHI ,  Hooman SHAYANI

IPC: G06F30/27 ,  G06N20/00 ,  G06T17/10 ,  G06F30/23

Abstract: In various embodiments, a parameter domain graph application generates UV-net representations of 3D CAD objects for machine learning models. In operation, the parameter domain graph application generates a graph based on a B-rep of a 3D CAD object. The parameter domain graph application discretizes a parameter domain of a parametric surface associated with the B-rep into a 2D grid. The parameter domain graph application computes at least one feature at a grid point included in the 2D grid based on the parametric surface to generate a 2D UV-grid. Based on the graph and the 2D UV-grid, the parameter domain graph application generates a UV-net representation of the 3D CAD object. Advantageously, generating UV-net representations of 3D CAD objects that are represented using B-reps enables the 3D CAD objects to be processed efficiently using neural networks.