SkexGen: Autoregressive Generation of CAD Construction Sequences with
Disentangled Codebooks
- URL: http://arxiv.org/abs/2207.04632v1
- Date: Mon, 11 Jul 2022 05:10:51 GMT
- Title: SkexGen: Autoregressive Generation of CAD Construction Sequences with
Disentangled Codebooks
- Authors: Xiang Xu, Karl D.D. Willis, Joseph G. Lambourne, Chin-Yi Cheng,
Pradeep Kumar Jayaraman, Yasutaka Furukawa
- Abstract summary: We present SkexGen, a novel autoregressive generative model for computer-aided design (CAD) construction sequences.
Autoregressive Transformer decoders generate CAD construction sequences sharing certain properties specified by the codebook vectors.
- Score: 37.33746656109331
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- FlexCAD: Unified and Versatile Controllable CAD Generation with Fine-tuned Large Language Models [22.010338370150738]
There is a growing interest in creating computer-aided design (CAD) models based on user intent.
Existing work offers limited controllability and needs separate models for different types of control.
We propose FlexCAD, a unified model by fine-tuning large language models.
arXiv Detail & Related papers (2024-11-05T05:45:26Z) - LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusion [46.76882780184126]
This paper introduces a novel hierarchical autoencoder that maps 3D models into a compressed latent space.
We show that the model can be used to represent a wide range of 3D models while faithfully representing high-resolution geometry details.
arXiv Detail & Related papers (2024-10-02T07:42:20Z) - PS-CAD: Local Geometry Guidance via Prompting and Selection for CAD Reconstruction [86.726941702182]
We introduce geometric guidance into the reconstruction network PS-CAD.
We provide the geometry of surfaces where the current reconstruction differs from the complete model as a point cloud.
Second, we use geometric analysis to extract a set of planar prompts, that correspond to candidate surfaces.
arXiv Detail & Related papers (2024-05-24T03:43:55Z) - ContrastCAD: Contrastive Learning-based Representation Learning for Computer-Aided Design Models [0.7373617024876725]
We propose a contrastive learning-based approach to learning CAD models, named ContrastCAD.
ContrastCAD effectively captures semantic information within the construction sequences of the CAD model.
We also propose a new CAD data augmentation method, called a Random Replace and Extrude (RRE) method, to enhance the learning performance of the model.
arXiv Detail & Related papers (2024-04-02T05:30:39Z) - Geometric Deep Learning for Computer-Aided Design: A Survey [85.79012726689511]
This survey offers a comprehensive overview of learning-based methods in computer-aided design.
It includes similarity analysis and retrieval, 2D and 3D CAD model synthesis, and CAD generation from point clouds.
It provides a complete list of benchmark datasets and their characteristics, along with open-source codes that have propelled research in this domain.
arXiv Detail & Related papers (2024-02-27T17:11:35Z) - Hierarchical Neural Coding for Controllable CAD Model Generation [34.14256897199849]
This paper presents a novel generative model for Computer Aided Design (CAD)
It represents high-level design concepts of a CAD model as a three-level hierarchical tree of neural codes.
It controls the generation or completion of CAD models by specifying the target design using a code tree.
arXiv Detail & Related papers (2023-06-30T21:49:41Z) - Towards Accurate Image Coding: Improved Autoregressive Image Generation
with Dynamic Vector Quantization [73.52943587514386]
Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm.
We propose a novel two-stage framework: (1) Dynamic-Quantization VAE (DQ-VAE) which encodes image regions into variable-length codes based their information densities for accurate representation.
arXiv Detail & Related papers (2023-05-19T14:56:05Z) - SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude
Operations [21.000539206470897]
SECAD-Net is an end-to-end neural network aimed at reconstructing compact and easy-to-edit CAD models.
We show superiority over state-of-the-art alternatives including the closely related method for supervised CAD reconstruction.
arXiv Detail & Related papers (2023-03-19T09:26:03Z) - AutoCAD: Automatically Generating Counterfactuals for Mitigating
Shortcut Learning [70.70393006697383]
We present AutoCAD, a fully automatic and task-agnostic CAD generation framework.
In this paper, we present AutoCAD, a fully automatic and task-agnostic CAD generation framework.
arXiv Detail & Related papers (2022-11-29T13:39:53Z) - DeepCAD: A Deep Generative Network for Computer-Aided Design Models [37.655225142981564]
We present the first 3D generative model for a drastically different shape representation -- describing a shape as a sequence of computer-aided design (CAD) operations.
Drawing an analogy between CAD operations and natural language, we propose a CAD generative network based on the Transformer.
arXiv Detail & Related papers (2021-05-20T03:29:18Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.