3D Shape Generation via Variational Autoencoder with Signed Distance Function Relativistic Average Generative Adversarial Network


Ajayi, Ebenezer Akinyemi and Lim, Kian Ming and Chong, Siew Chin and Lee, Chin Poo (2023) 3D Shape Generation via Variational Autoencoder with Signed Distance Function Relativistic Average Generative Adversarial Network. Applied Sciences, 13 (10). p. 5925. ISSN 2076-3417

[img] Text
applsci-13-05925-v2.pdf - Published Version
Restricted to Repository staff only

Download (1MB)


3D shape generation is widely applied in various industries to create, visualize, and analyse complex data, designs, and simulations. Typically, 3D shape generation uses a large dataset of 3D shapes as the input. This paper proposes a variational autoencoder with a signed distance function relativistic average generative adversarial network, referred to as 3D-VAE-SDFRaGAN, for 3D shape generation from 2D input images. Both the generative adversarial network (GAN) and variational autoencoder (VAE) algorithms are typical algorithms used to generate realistic 3D shapes. However, it is very challenging to train a stable 3D shape generation model using VAE-GAN. This paper proposes an efficient approach to stabilize the training process of VAE-GAN to generate high-quality 3D shapes. A 3D mesh-based shape is first generated using a 3D signed distance function representation by feeding a single 2D image into a 3D-VAE-SDFRaGAN network. The signed distance function is used to maintain inside–outside information in the implicit surface representation. In addition, a relativistic average discriminator loss function is employed as the training loss function. The polygon mesh surfaces are then produced via the marching cubes algorithm. The proposed 3D-VAE-SDFRaGAN is evaluated with the ShapeNet dataset. The experimental results indicate a notable enhancement in the qualitative performance, as evidenced by the visual comparison of the generated samples, as well as the quantitative performance evaluation using the chamfer distance metric. The proposed approach achieves an average chamfer distance score of 0.578, demonstrating superior performance compared to existing state-of-the-art models.

Item Type: Article
Uncontrolled Keywords: 3D shape generation; variational autoencoder; generative adversarial network; signed distance function; relativistic average
Subjects: T Technology > TR Photography
Divisions: Faculty of Information Science and Technology (FIST)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 03 Jul 2023 03:59
Last Modified: 03 Jul 2023 03:59
URII: http://shdl.mmu.edu.my/id/eprint/11492


Downloads per month over past year

View ItemEdit (login required)