Invention Publication
- Patent Title: MACHINE LEARNING TECHNIQUES FOR SKETCH-TO-3D SHAPE GENERATION
-
Application No.: US18488383Application Date: 2023-10-17
-
Publication No.: US20240331282A1Publication Date: 2024-10-03
- Inventor: Evan Patrick ATHERTON , Saeid ASGARI TAGHANAKI , Pradeep Kumar JAYARAMAN , Joseph George LAMBOURNE , Arianna RAMPINI , Aditya SANGHI , Hooman SHAYANI
- Applicant: AUTODESK, INC.
- Applicant Address: US CA San Francisco
- Assignee: AUTODESK, INC.
- Current Assignee: AUTODESK, INC.
- Current Assignee Address: US CA San Francisco
- Main IPC: G06T17/00
- IPC: G06T17/00 ; G06T11/20 ; 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.
Information query
IPC分类:
G | 物理 |
G06 | 计算;推算或计数 |
G06T | 一般的图像数据处理或产生 |
G06T17/00 | 用于计算机制图的3D建模 |