Publication | ACM Transactions on Graphics (SIGGRAPH Proceedings) 2021
Fusion 360 Gallery
A Dataset and Environment for Programmatic CAD Construction from Human Design Sequences
This paper presents the Fusion 360 Gallery reconstruction dataset, containing 8,625 human designed CAD sequences suitable for use with machine learning. The dataset enables learning-based approaches using human CAD design sequences for the first time, with the potential to improve customer workflows such as reverse engineering CAD files from 3D scan data.
Download publicationAbstract
Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design Sequences
Karl D.D. Willis, Yewen Pu, Jieliang Luo, Hang Chu, Tao Du, Joseph G. Lambourne, Armando Solar-Lezama, Wojciech Matusik
ACM Transactions on Graphics (SIGGRAPH Proceedings) 2021
Parametric computer-aided design (CAD) is a standard paradigm used to design manufactured objects, where a 3D shape is represented as a program supported by the CAD software. Despite the pervasiveness of parametric CAD and a growing interest from the research community, currently there does not exist a dataset of realistic CAD models in a concise programmatic form. In this paper we present the Fusion 360 Gallery, consisting of a simple language with just the sketch and extrude modeling operations, and a dataset of 8,625 human design sequences expressed in this language. We also present an interactive environment called the Fusion 360 Gym, which exposes the sequential construction of a CAD program as a Markov decision process, making it amendable to machine learning approaches. As a use case for our dataset and environment, we define the CAD reconstruction task of recovering a CAD program from a target geometry. We report results of applying state-of-the-art methods of program synthesis with neurally guided search on this task. Dataset and further information available at: https://github.com/AutodeskAILab/Fusion360GalleryDataset
Associated Autodesk Researchers
Jieliang (Rodger) Luo
Sr. Principal AI Research Scientist
Related Resources
2023
Deep Learning Methods of Cross-Modal Tasks for Conceptual Design of Product Shapes: A ReviewThis research highlights current challenges and proposes future…
2024
DesignQA: A Multimodal Benchmark for Evaluating Large Language Models’ Understanding of Engineering DocumentationNovel benchmark aimed at evaluating the proficiency of multimodal…
2024
HG-CAD: Hierarchical Graph Learning for Material Prediction and Recommendation in Computer-Aided DesignThis work presents a new Machine Learning architecture to support…
2022
SimCURL: Simple Contrastive User Representation Learning from Command SequencesUser modeling is crucial to understanding user behavior and essential…
Get in touch
Something pique your interest? Get in touch if you’d like to learn more about Autodesk Research, our projects, people, and potential collaboration opportunities.
Contact us