SkexGen: Autoregressive Generation of CAD Construction Sequences with Disentangled Codebooks

07/11/2022
by   Xiang Xu, et al.
11

We present SkexGen, a novel autoregressive generative model for computer-aided design (CAD) construction sequences containing sketch-and-extrude modeling operations. Our model utilizes distinct Transformer architectures to encode topological, geometric, and extrusion variations of construction sequences into disentangled codebooks. Autoregressive Transformer decoders generate CAD construction sequences sharing certain properties specified by the codebook vectors. Extensive experiments demonstrate that our disentangled codebook representation generates diverse and high-quality CAD models, enhances user control, and enables efficient exploration of the design space. The code is available at https://samxuxiang.github.io/skexgen.

READ FULL TEXT

page 7

page 9

page 18

page 19

page 20

page 21

page 22

page 23

research
06/30/2023

Hierarchical Neural Coding for Controllable CAD Model Generation

This paper presents a novel generative model for Computer Aided Design (...
research
03/26/2022

SolidGen: An Autoregressive Model for Direct B-rep Synthesis

The Boundary representation (B-rep) format is the de-facto shape represe...
research
07/05/2021

DeepRapper: Neural Rap Generation with Rhyme and Rhythm Modeling

Rap generation, which aims to produce lyrics and corresponding singing b...
research
11/11/2016

Construction Inspection through Spatial Database

This paper presents a novel pipeline for development of an efficient set...
research
09/05/2023

Representation Learning for Sequential Volumetric Design Tasks

Volumetric design, also called massing design, is the first and critical...
research
03/30/2021

Inferring CAD Modeling Sequences Using Zone Graphs

In computer-aided design (CAD), the ability to "reverse engineer" the mo...
research
04/22/2017

CAD Adjacency Computation Using Validated Numerics

We present an algorithm for computation of cell adjacencies for well-bas...

Please sign up or login with your details

Forgot password? Click here to reset