Parametric computer-aided design (CAD) is a standard paradigm used for the
design of manufactured objects. CAD designers perform modeling operations, such
as sketch and extrude, to form a construction sequence that makes up a final
design. Despite the pervasiveness of parametric CAD and growing interest from
the research community, a dataset of human designed 3D CAD construction
sequences has not been available to-date. In this paper we present the Fusion
360 Gallery reconstruction dataset and environment for learning CAD
reconstruction. We provide a dataset of 8,625 designs, comprising sequential
sketch and extrude modeling operations, together with a complementary
environment called the Fusion 360 Gym, to assist with performing CAD
reconstruction. We outline a standard CAD reconstruction task, together with
evaluation metrics, and present results from a novel method using neurally
guided search to recover a construction sequence from raw geometry.
Description
[2010.02392] Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Reconstruction
%0 Generic
%1 willis2020fusion
%A Willis, Karl D. D.
%A Pu, Yewen
%A Luo, Jieliang
%A Chu, Hang
%A Du, Tao
%A Lambourne, Joseph G.
%A Solar-Lezama, Armando
%A Matusik, Wojciech
%D 2020
%K 2020 cad dataset reconstruction
%T Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD
Reconstruction
%U http://arxiv.org/abs/2010.02392
%X Parametric computer-aided design (CAD) is a standard paradigm used for the
design of manufactured objects. CAD designers perform modeling operations, such
as sketch and extrude, to form a construction sequence that makes up a final
design. Despite the pervasiveness of parametric CAD and growing interest from
the research community, a dataset of human designed 3D CAD construction
sequences has not been available to-date. In this paper we present the Fusion
360 Gallery reconstruction dataset and environment for learning CAD
reconstruction. We provide a dataset of 8,625 designs, comprising sequential
sketch and extrude modeling operations, together with a complementary
environment called the Fusion 360 Gym, to assist with performing CAD
reconstruction. We outline a standard CAD reconstruction task, together with
evaluation metrics, and present results from a novel method using neurally
guided search to recover a construction sequence from raw geometry.
@misc{willis2020fusion,
abstract = {Parametric computer-aided design (CAD) is a standard paradigm used for the
design of manufactured objects. CAD designers perform modeling operations, such
as sketch and extrude, to form a construction sequence that makes up a final
design. Despite the pervasiveness of parametric CAD and growing interest from
the research community, a dataset of human designed 3D CAD construction
sequences has not been available to-date. In this paper we present the Fusion
360 Gallery reconstruction dataset and environment for learning CAD
reconstruction. We provide a dataset of 8,625 designs, comprising sequential
sketch and extrude modeling operations, together with a complementary
environment called the Fusion 360 Gym, to assist with performing CAD
reconstruction. We outline a standard CAD reconstruction task, together with
evaluation metrics, and present results from a novel method using neurally
guided search to recover a construction sequence from raw geometry.},
added-at = {2021-05-06T15:08:15.000+0200},
author = {Willis, Karl D. D. and Pu, Yewen and Luo, Jieliang and Chu, Hang and Du, Tao and Lambourne, Joseph G. and Solar-Lezama, Armando and Matusik, Wojciech},
biburl = {https://www.bibsonomy.org/bibtex/29056a7de54f407b00fbcbf4ef50a8f36/analyst},
description = {[2010.02392] Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Reconstruction},
interhash = {3fe5adaa0f950afe1a152d084b19f0a7},
intrahash = {9056a7de54f407b00fbcbf4ef50a8f36},
keywords = {2020 cad dataset reconstruction},
note = {cite arxiv:2010.02392},
timestamp = {2021-05-06T15:08:15.000+0200},
title = {Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD
Reconstruction},
url = {http://arxiv.org/abs/2010.02392},
year = 2020
}