公开(公告)号：US20250157164A1

公开(公告)日：2025-05-15

申请号：US18506974

申请日：2023-11-10

Applicant: Autodesk, Inc.

Inventor： Ajay Vijayabalan Menon ,  João Lucas Lautenschlager Cortez Alves ,  Gabriel M. Paez ,  Shyam Prathish Sargunam

IPC: G06T19/20 ,  G06F3/01 ,  G06F3/0346

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for computer aided design of physical structures include: rendering, to a display device of a first user, a first user's view into an extended reality environment, the first user's view being generated using a first pose being tracked for the first user; identifying that a first avatar associated with the first user has entered a shared perspective mode with a second avatar associated with a second user of the XR environment, wherein the shared perspective mode has a single frame of reference in the XR environment that is shared by the first user and the second user; and performing, while in the shared perspective mode, the rendering to the display device of the first user.

公开(公告)号：US20250157118A1

公开(公告)日：2025-05-15

申请号：US18916487

申请日：2024-10-15

Applicant: AUTODESK, INC.

Inventor： Qian ZHOU ,  Fraser ANDERSON ,  George William FITZMAURICE ,  David Ledo MAIRA

IPC: G06T13/40

Abstract: A technique for modifying character animations via a user interface, including displaying a timeline that includes frame numbers as time units, displaying a set of keyposes of the character along the timeline based on a set of frame numbers associated with the set of keyposes, displaying a set of trajectories that is superimposed on the set of keyposes, wherein each trajectory in the set of trajectories is displayed as a curve that passes through a particular joint of the character across the set of keyposes, and receiving a modification of a first keypose included in the set of keyposes via the user interface. A technique for automatically extracting a set of keyposes from a character animation based on the plurality of joint trajectories. A technique for retiming segments of a character animation.

公开(公告)号：US20250156611A1

公开(公告)日：2025-05-15

申请号：US18944784

申请日：2024-11-12

Applicant: Autodesk, Inc.

Inventor： Sam Robert Jamieson ,  Jason Lao ,  Marco Antonio Rodrigues Andrade ,  Siavash Hakim Elahi ,  Vishnu Prathish ,  Gerald Brown ,  Samer Muhandes ,  Maciek Tytus Rybczynski

IPC: G06F30/28 ,  G06F30/27 ,  G06N3/08

Abstract: A method and system provide for generating a stormwater overland flow map. Simulation inputs (ground surface data) and simulation outputs (stormwater overland flow maps) are obtained from a deluge simulation model that simulates where water will channel and accumulate on a surface. A convolutional neural network (CNN) is trained to approximate the simulation outputs of the deluge simulation model. The CNN is a sequence of CNN models that each represent a time step and each CNN model in the sequence takes CNN output from a previous CNN model as its input. The CNN output is a video output and a visual representation of stormwater overland flow over time. A new input is a first format is obtained. A collection of custom objects representing points of a grid are stored and includes z-values of points on the surface and stormwater controls. The grid is populated and then processed in/by the CNN.

公开(公告)号：US20250148162A1

公开(公告)日：2025-05-08

申请号：US18821981

申请日：2024-08-30

Applicant: AUTODESK, INC.

Inventor： Hyunmin CHEONG ,  Mehran EBRAHIMI ,  Adrian BUTSCHER ,  Hesam SALEHIPOUR

IPC: G06F30/20

Abstract: In various embodiments, a generative design application can leverage multi-disciplinary optimization to solve a design problem associated with a 3D model and interdependent design variables. The generative design application includes an optimization engine that can solve the design problem, or portions thereof, by iteratively performing optimization techniques on the interdependent design variables to generate an 3D model that maximizes or minimizes one or more objectives and meets one or more constraints, while simultaneously considering the effect of each interdependency of the design variables. Furthermore, the generative design application can leverage a natural language interface to augment the creation of the design problem for optimization. The generative design application can also leverage free-form deformation during generative design to parameterize a portion of the 3D model as part of the design problem.

公开(公告)号：US20250148161A1

公开(公告)日：2025-05-08

申请号：US18821940

申请日：2024-08-30

Applicant: AUTODESK, INC.

Inventor： Hyunmin CHEONG ,  Mehran EBRAHIMI ,  Adrian BUTSCHER ,  Hesam SALEHIPOUR

IPC: G06F30/20

Abstract: In various embodiments, a generative design application can leverage multi-disciplinary optimization to solve a design problem associated with a 3D model and interdependent design variables. The generative design application includes an optimization engine that can solve the design problem, or portions thereof, by iteratively performing optimization techniques on the interdependent design variables to generate an 3D model that maximizes or minimizes one or more objectives and meets one or more constraints, while simultaneously considering the effect of each interdependency of the design variables. Furthermore, the generative design application can leverage a natural language interface to augment the creation of the design problem for optimization. The generative design application can also leverage free-form deformation during generative design to parameterize a portion of the 3D model as part of the design problem.

公开(公告)号：US12293136B2

公开(公告)日：2025-05-06

申请号：US17099552

申请日：2020-11-16

Applicant: AUTODESK, INC.

Inventor： David Benjamin ,  Rui Wang ,  Dale Zhao

IPC: G06F30/13 ,  G06F111/04

Abstract: One or more embodiments disclose techniques for generating a layout for a physical space or a building. The techniques include generating a layout based on a floorplan of a physical space, generating a plurality of spatial unit grids corresponding to a plurality of spatial units to be placed in the physical space, identifying a placement for a first spatial unit grid in the plurality of spatial unit grids within the layout by matching a corner cell in the first spatial unit grid with a given available cell in the layout, generating a score associated with the placement for the first spatial unit grid based on one or more placement parameters that define placement constraints for a first spatial unit included in the plurality of spatial units and corresponding to the first spatial unit grid, and placing the first spatial unit grid in the layout based on the score.

公开(公告)号：US20250139926A1

公开(公告)日：2025-05-01

申请号：US19005915

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 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：US20250139337A1

公开(公告)日：2025-05-01

申请号：US18918955

申请日：2024-10-17

Applicant: AUTODESK, INC.

Inventor： George William FITZMAURICE ,  Jo Karel VERMEULEN ,  Justin Frank MATEJKA

IPC: G06F30/27 ,  G06F30/12

Abstract: A computer-implemented method for generating design objects for computer-aided drawing (CAD) design, comprises combining at least two of a first input received from a first client device and one or more persistent intents to generate a composite prompt, inputting the composite prompt into a trained machine learning (ML) model for execution, receiving a design object generated by the trained ML model in response to the composite prompt; and displaying the design object in a design space that includes the CAD design.

公开(公告)号：US20250139315A1

公开(公告)日：2025-05-01

申请号：US18500033

申请日：2023-11-01

Applicant: AUTODESK, INC.

Inventor： Bokyung LEE ,  Rhys GOLDSTEIN ,  Damon LAU ,  Michael LEE ,  Jeremy MOGK ,  Jacobo Bibliowicz SCHUSTER ,  Alexander TESSIER

IPC: G06F30/13 ,  G06F30/20

Abstract: In various embodiments, a building layout application generates building designs that reduce virus transmissions. The building layout application generates a first layout design set for a building based on a first design vector set and a baseline layout design. The building layout application executes, multiple times, a stochastic multi-agent virus simulator on a layout design included in the first layout design set and a simulation configuration to generate simulation results. The building layout application computes a risk score associated with both the layout design and a virus based on the simulation results. The building layout application executes evolutionary operations(s) on the first design vector set based on the risk score and at least one other risk score to generate a second design vector set. The building layout application generates a second layout design set for the building based on the second design vector set and the baseline layout design.

公开(公告)号：US12288013B2

公开(公告)日：2025-04-29

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 ,  G06F30/23 ,  G06N20/00 ,  G06T17/10

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.