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.

公开(公告)号：US20220156415A1

公开(公告)日：2022-05-19

申请号：US17523725

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: G06F30/10

Abstract: In various embodiments, a style comparison metric application generates a style comparison metric for pairs of different three dimensional (3D) computer-aided design (CAD) objects. In operation, the style comparison metric application executes a trained neural network any number of times to map 3D CAD objects to feature maps. Based on the feature maps, the style comparison metric application computes style signals. The style comparison metric application determines values for weights based on the style signals. The style comparison metric application generates the style comparison metric based on the weights and a parameterized style comparison metric.

公开(公告)号：US20210117589A1

公开(公告)日：2021-04-22

申请号：US16898194

申请日：2020-06-10

Applicant: AUTODESK, INC.

Inventor： Andriy BANADYHA ,  Hooman SHAYANI ,  Anthony RUTO ,  Bhupendra LODHIA

IPC: G06F30/20 ,  G06F30/10 ,  B29C64/20 ,  A43B17/00

Abstract: A computer-implemented method of generating one or more variable stiffness structures includes determining a thickness of a first portion of a variable stiffness structure; determining a pressure that is to be applied to a surface of the first portion; selecting a first predetermined value for a stiffness attribute based on the thickness of the first portion and the pressure; and generating a model of at least part of the variable stiffness structure that includes the first portion, wherein the first portion has the predetermined value for the stiffness attribute.

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：US20190155966A1

公开(公告)日：2019-05-23

申请号：US16192657

申请日：2018-11-15

Applicant: AUTODESK, INC.

Inventor： Mehdi NOURBAKHSH ,  Adrian BUTSCHER ,  Hooman SHAYANI

IPC: G06F17/50

Abstract: One embodiment of the present invention sets forth a technique for generating one or more designs for a structural frame, the method comprising: receiving an input frame and an optimization objective that indicates a design goal for the one or more designs; based on the input frame, generating multiple candidate frames via a divergent search algorithm; based on the optimization objective, generating a different solution frame for each candidate frame via a convergent search algorithm; and determining a quality factor for each solution frame that enables a quantitative comparison with respect to the optimization objective of the solution frame with each other solution frame.