SWAGE-3D: Spectral Wasserstein Attention Generative Ensemble, A Comparative Analysis on the ShapeNet Dataset

Zafer Serin^1,*, Cihan Karakuzu², Uğur Yüzgeç²
1 Pazaryeri Vocational School, Bilecik Seyh Edebali University, Bilecik, Türkiye
2 Department of Computer Engineering, Bilecik Seyh Edebali University, Bilecik, Türkiye
* Corresponding Author: Zafer Serin. Email: email
(This article belongs to the Special Issue: AI-Enhanced Computational Methods in Engineering and Physical Science)

Computer Modeling in Engineering & Sciences https://doi.org/10.32604/cmes.2026.079254

Received 18 January 2026; Accepted 20 March 2026; Published online 30 April 2026

Download PDF

Abstract

This study proposes SWAGE-3D (Spectral Wasserstein Attention Generative Ensemble), an enhanced 3D-VAE-GAN framework for single-view 3D object reconstruction using voxel-based representations. The proposed model integrates RGB-D encoding, Wasserstein adversarial learning with hybrid Lipschitz regularization, and a self-attention–augmented generator to improve structural coherence and training stability. By combining variational latent modeling with stabilized Wasserstein optimization, the framework aims to address common challenges in 3D generative modeling, including mode collapse, unstable convergence, and insufficient global consistency. The encoder employs a depth-aware feature extraction strategy, while the discriminator utilizes a hybrid spectral normalization and gradient penalty mechanism to ensure robust approximation of the Wasserstein objective. Additionally, an ensemble strategy is applied at inference time to enhance reconstruction reliability. The proposed approach is evaluated on the ShapeNet dataset across 13 object categories using the Intersection over Union (IoU) metric. Experimental results demonstrate a 16.7% improvement over the baseline 3D-VAE-GAN and competitive performance against state-of-the-art voxel-based reconstruction methods. These findings confirm that the synergistic integration of depth cues, stabilized Wasserstein training, and attention mechanisms significantly enhances single-view 3D reconstruction performance.

Graphical Abstract

SWAGE-3D: Spectral Wasserstein Attention Generative Ensemble, A Comparative Analysis on the ShapeNet Dataset

Keywords

Three-dimensional reconstruction; variational autoencoder; generative adversarial network; depth estimation; residual neural network; ensemble learning; attention mechanism