Abstract

Generative artificial intelligence (AI) models have made significant progress in automating the creation of 3D shapes, which has the potential to transform car design. In engineering design and optimization, evaluating engineering metrics is crucial. To make generative models performance-aware and enable them to create high-performing designs, surrogate modeling of these metrics is necessary. However, the currently used representations of 3D shapes either require extensive computational resources to learn or suffer from significant information loss, which impairs their effectiveness in surrogate modeling. To address this issue, we propose a new 2D representation of 3D shapes. We develop a surrogate drag model based on this representation to verify its effectiveness in predicting 3D car drag. We construct a diverse dataset of 4535 high-quality 3D car meshes labeled by drag coefficients computed from computational fluid dynamics simulations to train our model. Our experiments demonstrate that our model can accurately and efficiently evaluate drag coefficients with an R2 value above 0.84 for various car categories. Our model is implemented using deep neural networks, making it compatible with recent AI image generation tools (such as stable diffusion) and a significant step toward the automatic generation of drag-optimized car designs. Moreover, we demonstrate a case study using the proposed surrogate model to guide a diffusion-based deep generative model for drag-optimized car body synthesis.

Graphical Abstract Figure
Graphical Abstract Figure
Close modal

References

1.
Wang
,
N.
,
Zhang
,
Y.
,
Li
,
Z.
,
Fu
,
Y.
,
Liu
,
W.
, and
Jiang
,
Y. G.
,
2018
, “
Pixel2Mesh: Generating 3D Mesh Models From Single RGB Images
,”
Proceedings of the European Conference on Computer Vision (ECCV)
,
Munich, Germany
,
Sept. 8–14
, Vol. 11215, pp.
55
71
.
2.
Zhou
,
L.
,
Du
,
Y.
, and
Wu
,
J.
,
2021
, “
3D Shape Generation and Completion Through Point-Voxel Diffusion
,”
the IEEE International Conference on Computer Vision
,
Virtual
,
Oct. 11–17
, Vol. 4, pp.
5806
5815
.
3.
Zeng
,
X.
,
Vahdat
,
A.
,
Williams
,
F.
,
Gojcic
,
Z.
,
Litany
,
O.
,
Fidler
,
S.
, and
Kreis
,
K.
,
2022
, LION: Latent Point Diffusion Models for 3D Shape Generation”.
4.
Nichol
,
A.
,
Jun
,
H.
,
Dhariwal
,
P.
,
Mishkin
,
P.
, and
Chen
,
M.
,
2022
, Point-E: A System for Generating 3D Point Clouds from Complex Prompts”.
5.
Nichol
,
A.
,
Dhariwal
,
P.
,
Ramesh
,
A.
,
Shyam
,
P.
,
Mishkin
,
P.
,
McGrew
,
B.
,
Sutskever
,
I.
, and
Chen
,
M.
,
2021
, GLIDE: Towards Photorealistic Image Generation and Editing With Text-Guided Diffusion Models”.
6.
Prokhorov
,
D.
,
2010
, “
A Convolutional Learning System for Object Classification in 3-D LIDAR Data
,”
IEEE Trans. Neural Netw.
,
21
(
5
), pp.
858
863
.
7.
Maturana
,
D.
, and
Scherer
,
S.
,
2015
, “
VoxNet: A 3D Convolutional Neural Network for Real-Time Object Recognition
,” In 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS),
IEEE
, pp.
922
928
.
8.
Li
,
X.
,
Xie
,
C.
, and
Sha
,
Z.
,
2022
, “
A Predictive and Generative Design Approach for Three-Dimensional Mesh Shapes Using Target-Embedding Variational Autoencoder
,”
ASME J. Mech. Des.
,
144
(
11
), p.
114501
.
9.
Qi
,
C. R.
,
Su
,
H.
,
Niessner
,
M.
,
Dai
,
A.
,
Yan
,
M.
, and
Guibas
,
L. J.
,
2016
, “
Volumetric and Multi-view CNNs for Object Classification on 3D Data
,”
he IEEE Computer Society Conference on Computer Vision and Pattern Recognition
,
Las Vegas, NV
,
June 27–30
, pp.
5648
5656
.
10.
Wang
,
C.
,
Pelillo
,
M.
, and
Siddiqi
,
K.
,
2019
, “
Dominant Set Clustering and Pooling for Multi-view 3D Object Recognition
,”
British Machine Vision Conference
,
London, UK
,
Sept. 4–7
, p.
6
.
11.
Masci
,
J.
,
Boscaini
,
D.
,
Bronstein
,
M. M.
, and
Vandergheynst
,
P.
,
2015
, “
Geodesic Convolutional Neural Networks on Riemannian Manifolds
,”
the IEEE International Conference on Computer Vision
,
Santiago, Chile
,
Dec. 7–13
, pp.
832
840
.
12.
Luo
,
S.
, and
Hu
,
W.
,
2021
, “
Diffusion Probabilistic Models for 3D Point Cloud Generation
,”
the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
,
Virtual
,
June 19–25
, Vol. 3, pp.
2836
2844
.
13.
Ghadai
,
S.
,
Lee
,
X. Y.
,
Balu
,
A.
,
Sarkar
,
S.
, and
Krishnamurthy
,
A.
,
2021
, “
Multi-resolution 3D CNN for Learning Multi-scale Spatial Features in CAD Models
,”
Comput. Aided Geometr. Des.
,
91
, p.
102038
.
14.
Su
,
H.
,
Maji
,
S.
,
Kalogerakis
,
E.
, and
Learned-Miller
,
E.
,
2015
, “
Multi-view Convolutional Neural Networks for 3D Shape Recognition
,”
the IEEE International Conference on Computer Vision
,
Santiago, Chile
,
Dec. 7–13
, Vol. 2015, pp.
945
953
.
15.
Achlioptas
,
P.
,
Diamanti
,
O.
,
Mitliagkas
,
I.
, and
Guibas
,
L.
,
2017
, “
Learning Representations and Generative Models for 3D Point Clouds
,”
35th International Conference on Machine Learning
,
Stockholm, Sweden
,
July 10–15
, Vol. 1, pp.
67
85
.
16.
Gunpinar
,
E.
,
Coskun
,
U. C.
,
Ozsipahi
,
M.
, and
Gunpinar
,
S.
,
2019
, “
A Generative Design and Drag Coefficient Prediction System for Sedan Car Side Silhouettes Based on Computational Fluid Dynamics
,”
Comput. Aided Des.
,
111
, pp.
65
79
.
17.
Umetani
,
N.
, and
Bickel
,
B.
,
2018
, “
Learning Three-Dimensional Flow for Interactive Aerodynamic Design
,”
ACM Trans. Graph. (TOG)
,
37
(
4
), p.
10
.
18.
Badías
,
A.
,
Curtit
,
S.
,
González
,
D.
,
Alfaro
,
I.
,
Chinesta
,
F.
, and
Cueto
,
E.
,
2019
, “
An Augmented Reality Platform for Interactive Aerodynamic Design and Analysis
,”
Int. J. Numer. Methods Eng.
,
120
(
1
), pp.
125
138
.
19.
Garcia-Garcia
,
A.
,
Gomez-Donoso
,
F.
,
Garcia-Rodriguez
,
J.
,
Orts-Escolano
,
S.
,
Cazorla
,
M.
, and
Azorin-Lopez
,
J.
,
2016
, PointNet: A 3D Convolutional Neural Network for Real-Time Object Class Recognition.
20.
Tatarchenko
,
M.
,
Dosovitskiy
,
A.
, and
Brox
,
T.
,
2017
, “
Octree Generating Networks: Efficient Convolutional Architectures for High-Resolution 3D Outputs
,”
the IEEE International Conference on Computer Vision
,
Venice, Italy
,
Oct. 22–29
, pp.
2088
2096
.
21.
Wu
,
Z.
,
Song
,
S.
,
Khosla
,
A.
,
Yu
,
F.
,
Zhang
,
L.
,
Tang
,
X.
, and
Xiao
,
J.
,
2015
, 3D ShapeNets: A Deep Representation for Volumetric Shapes.
22.
Wang
,
C.
,
Samari
,
B.
, and
Siddiqi
,
K.
,
2018
, “
Local Spectral Graph Convolution for Point Set Feature Learning
,”
the European conference on computer vision
,
Munich, Germany
,
Sept. 8–14
, Vol. 11208, pp.
56
71
.
23.
Boscaini
,
D.
,
Masci
,
J.
,
Rodolà
,
E.
, and
Bronstein
,
M.
,
2016
, “
Learning Shape Correspondence With Anisotropic Convolutional Neural Networks
,”
Advances in Neural Information Processing Systems
,
Barcelona, Spain
,
Dec. 5–10
, p.
29
.
24.
Wang
,
D. Z.
, and
Posner
,
I.
,
2015
, “
Voting for Voting in Online Point Cloud Object Detection
,”
Robotics: Science and Systems
,
Rome, Italy
,
July 13–17
.
25.
Li
,
Y.
,
Pirk
,
S.
,
Su
,
H.
,
Qi
,
C. R.
, and
Guibas
,
L. J.
,
2016
, “
FPNN: Field Probing Neural Networks for 3D Data
,”
Advances in Neural Information Processing Systems
,
Barcelona, Spain
,
Dec. 5–10
, Vol. 5, pp.
307
315
.
26.
Fey
,
M.
,
Lenssen
,
J. E.
,
Weichert
,
F.
, and
Müller
,
H.
,
2017
, “
SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels
,”
the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
,
Honolulu, HI
,
July 21–26
, Vol. 11, pp.
869
877
.
27.
Li
,
J.
,
Chen
,
B. M.
, and
Lee
,
G. H.
,
2018
, “
SO-Net: Self-Organizing Network for Point Cloud Analysis
,”
the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
,
Salt Lake City, UT
,
June 18–23
, Vol. 12, pp.
9397
9406
.
28.
Michel
,
O.
,
Bar-On
,
R.
,
Liu
,
R.
,
Benaim
,
S.
, and
Hanocka
,
R.
,
2021
, “Text2Mesh: Text-Driven Neural Stylization for Meshes”.
29.
Jetchev
,
N.
,
2021
, “ClipMatrix: Text-Controlled Creation of 3D Textured Meshes”.
30.
Maron
,
H.
,
Galun
,
M.
,
Aigerman
,
N.
,
Trope
,
M.
,
Dym
,
N.
,
Yumer
,
E.
,
Kim
,
V. G.
, and
Lipman
,
Y.
,
2017
, “
Convolutional Neural Networks on Surfaces Via Seamless Toric Covers
,”
ACM Trans. Graph. (TOG)
,
36
(
4
), pp.
71
1
.
31.
Ben-Hamu
,
H.
,
Maron
,
H.
,
Kezurer
,
I.
,
Avineri
,
G.
, and
Lipman
,
Y.
,
2018
, “
Multi-chart Generative Surface Modeling
”.
SIGGRAPH Asia 2018 Technical Papers, SIGGRAPH Asia 2018
, p.
6
.
32.
Saquil
,
Y.
,
Xu
,
Q. C.
,
Yang
,
Y. L.
, and
Hall
,
P.
,
2020
, “
Rank3DGAN: Semantic Mesh Generation Using Relative Attributes
,”
34th AAAI Conference on Artificial Intelligence
,
New York
,
Feb. 7–12
, pp.
5586
5594
.
33.
Alhaija
,
H. A.
,
Dirik
,
A.
,
Knörig
,
A.
,
Fidler
,
S.
, and
Shugrina
,
M.
,
2022
, “
XDGAN: Multi-modal 3D Shape Generation in 2D Space
”.
34.
Chen
,
Z.
, and
Zhang
,
H.
,
2018
, “
Learning Implicit Fields for Generative Shape Modeling
,”
the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
,
Salt Lake City, UT
,
June 18–23
, pp.
5932
5941
.
35.
Park
,
J. J.
,
Florence
,
P.
,
Straub
,
J.
,
Newcombe
,
R.
, and
Lovegrove
,
S.
,
2019
, “
DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation
,”
the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
,
Long Beach, CA
,
June 15–20
, Vol. 1, pp.
165
174
.
36.
Alwala
,
K. V.
,
Gupta
,
A.
, and
Tulsiani
,
S.
,
2022
, “
Pre-Train, Self-Train, Distill: A Simple Recipe for Supersizing 3D Reconstruction
”. pp.
3763
3772
.
37.
Liu
,
Z.
,
Dai
,
P.
,
Li
,
R.
,
Qi
,
X.
, and
Fu
,
C.-W.
,
2022
, “
ISS: Image as Stepping Stone for Text-Guided 3D Shape Generation
.”
38.
de Avila Belbute-Peres
,
F.
,
Economon
,
T. D.
, and
Kolter
,
J. Z.
,
2020
, “
Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Prediction
,”
the 37th International Conference on Machine Learning
,
Virtual
,
July 13–18
.
39.
Rosset
,
N.
,
Cordonnier
,
G.
,
Duvigneau
,
R.
,
Bousseau
,
A.
, and
Rosset Guillaume Cordonnier Regis Duvigneau Adrien Bousseau
,
N.
,
2023
, “
Interactive Design of 2D Car Profiles With Aerodynamic Feedback
,”
Comput. Graph. Forum
,
42
(
2
), pp.
1
11
.
40.
Remelli
,
E.
,
Lukoianov
,
A.
,
Richter
,
S. R.
,
Guillard
,
B.
,
Bagautdinov
,
T.
,
Baque
,
P.
, and
Fua
,
P.
,
2020
, “
MeshSDF: Differentiable Iso-Surface Extraction
,”
Advances in Neural Information Processing Systems
,
Virtual
,
Dec. 6–12
, p.
6
.
41.
Baque
,
P.
,
Remelli
,
E.
,
Fleuret
,
F.
, and
Fua
,
P.
,
2018
, “
Geodesic Convolutional Shape Optimization
,”
35th International Conference on Machine Learning
,
Stockholm, Sweden
,
July 10–15
, pp.
797
809
.
42.
Jacob
,
S. J.
,
Mrosek
,
M.
,
Othmer
,
C.
, and
Köstler
,
H.
,
2021
, “
Deep Learning for Real-Time Aerodynamic Evaluations of Arbitrary Vehicle Shapes
,”
SAE International Journal of Passenger Vehicle Systems
,
15
(
2
), pp.
77
90
.
43.
Durasov
,
N.
,
Lukoyanov
,
A.
,
Donier
,
J.
, and
Fua
,
P.
,
2021
,
DEBOSH: Deep Bayesian Shape Optimization
.
44.
Thuerey
,
N.
,
Weissenow
,
K.
,
Prantl
,
L.
, and
Hu
,
X.
,
2018
, “
Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows
,”
AIAA J.
,
58
(
1
), pp.
25
36
.
45.
Saha
,
S.
,
Rios
,
T.
,
Minku
,
L. L.
,
Stein
,
B. V.
,
Wollstadt
,
P.
,
Yao
,
X.
,
Back
,
T.
,
Sendhoff
,
B.
, and
Menzel
,
S.
,
2021
, “
Exploiting Generative Models for Performance Predictions of 3D Car Designs
,”
2021 IEEE Symposium Series on Computational Intelligence
,
Orlando, FL
,
Dec. 5–7
.
46.
Xin
,
D.
,
Zeng
,
J.
, and
Xue
,
K.
,
2022
, “
Surrogate Drag Model of Non-Spherical Fragments Based on Artificial Neural Networks
,”
Powder Technol.
,
404
, p.
117412
.
47.
TAO
,
J.
,
SUN
,
G.
,
GUO
,
L.
, and
WANG
,
X.
,
2020
, “
Application of a PCA-DBN-based Surrogate Model to Robust Aerodynamic Design Optimization
,”
Chin. J. Aeronaut.
,
33
(
6
), pp.
1573
1588
.
48.
Sun
,
G.
, and
Wang
,
S.
, “
A Review of the Artificial Neural Network Surrogate Modeling in Aerodynamic Design
”.
49.
Chang
,
A. X.
,
Funkhouser
,
T.
,
Guibas
,
L.
,
Hanrahan
,
P.
,
Huang
,
Q.
,
Li
,
Z.
,
Savarese
,
S.
,
Savva
,
M.
,
Song
,
S.
,
Su
,
H.
,
Xiao
,
J.
,
Yi
,
L.
, and
Yu
,
F.
,
2015
, “
ShapeNet: An Information-Rich 3D Model Repository
”.
50.
Biswas
,
K.
,
Gadekar
,
G.
, and
Chalipat
,
S.
,
2019
, “
Development and Prediction of Vehicle Drag Coefficient Using OpenFoam CFD Tool
”.
SAE Technical Papers
,
2019
(
January
),
1
.
51.
Heft
,
A. I.
,
Indinger
,
T.
, and
Adams
,
N. A.
,
2012
, “
Introduction of a New Realistic Generic Car Model for Aerodynamic Investigations
”.
SAE Technical Papers
,
4
.
52.
Szegedy
,
C.
,
Vanhoucke
,
V.
,
Ioffe
,
S.
,
Shlens
,
J.
, and
Wojna
,
Z.
,
2016
, “
Rethinking the Inception Architecture for Computer Vision
,”
the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
,,
Las Vegas, NV
,
June 27–30
, pp.
2818
2826
.
53.
He
,
K.
,
Zhang
,
X.
,
Ren
,
S.
, and
Sun
,
J.
,
2016
, “
Deep Residual Learning for Image Recognition
,”
the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
,
Las Vegas, NV
,
June 27–30
, pp.
770
778
.
54.
Xie
,
S.
,
Girshick
,
R.
,
Dollár
,
P.
,
Tu
,
Z.
, and
He
,
K.
,
2016
, “
Aggregated Residual Transformations for Deep Neural Networks
,”
30th IEEE Conference on Computer Vision and Pattern Recognition
,
Honolulu, HI
,
July 21–26
, pp.
5987
5995
.
55.
Dosovitskiy
,
A.
,
Beyer
,
L.
,
Kolesnikov
,
A.
,
Weissenborn
,
D.
,
Zhai
,
X.
,
Unterthiner
,
T.
,
Dehghani
,
M.
,
Minderer
,
M.
,
Heigold
,
G.
,
Gelly
,
S.
,
Uszkoreit
,
J.
, and
Houlsby
,
N.
,
2020
, “
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
”.
56.
Du
,
C.
,
Li
,
T.
,
Liu
,
Y.
,
Wen
,
Z.
,
Hua
,
T.
,
Wang
,
Y.
, and
Zhao
,
H.
,
2021
, “
Improving Multi-modal Learning With Uni-modal Teachers
”.
57.
Song
,
B.
,
Associate
,
P.
,
Miller
,
S.
, and
Ahmed
,
F.
,
2023
, “
Attention-Enhanced Multimodal Learning for Conceptual Design Evaluations
,”
ASME J. Mech. Des.
,
145
(
4
), p.
041410
.
58.
Jacob
,
S. J.
,
Mrosek
,
M.
,
Othmer
,
C.
, and
Köstler
,
H.
,
2022
, “
Deep Learning for Real-Time Aerodynamic Evaluations of Arbitrary Vehicle Shapes
,”
SAE Int. J. Passenger Vehicle Syst.
,
15
(
2
), pp.
77
90
.
59.
Cunningham
,
J. D.
,
Simpson
,
T. W.
, and
Tucker
,
C. S.
,
2019
, “
An Investigation of Surrogate Models for Efficient Performance-Based Decoding of 3D Point Clouds
,”
ASME J. Mech. Des.
,
141
(
12
), p.
121401
.
60.
Abbas
,
A.
,
Rafiee
,
A.
,
Haase
,
M.
, and
Malcolm
,
A.
,
2022
, “
Geometrical Deep Learning for Performance Prediction of High-Speed Craft
,”
Ocean Eng.
,
258
, p.
111716
.
61.
Ho
,
J.
,
Jain
,
A.
, and
Abbeel
,
P.
,
2020
, “
“Denoising Diffusion Probabilistic Models”
,”
Advances in Neural Information Processing Systems
,
Virtual
,
Dec. 6–12
, p.
6
.
62.
Mazé
,
F.
, and
Ahmed
,
F.
,
2023
, “
Diffusion Models Beat GANs on Topology Optimization
,”
the AAAI Conference on Artificial Intelligence
,
Philadelphia, PA
,
Feb. 27–Mar. 2
, Vol. 37, pp.
9108
9116
.
63.
Dhariwal
,
P.
, and
Nichol
,
A.
,
2021
, “
Diffusion Models Beat GANs on Image Synthesis
,”
Advances in Neural Information Processing Systems
,
Virtual
,
Dec. 6–14
, Vol. 11, pp.
8780
8794
.
You do not currently have access to this content.