FacadeGAN: Facade Texture Placement with GANs
Open Access
- 14 January 2026
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 16 (2) , 860
Abstract
This study presents a texture-aware image synthesis framework designed to generate material-consistent façades using adversarial learning. The proposed architecture incorporates a mask-guided channel-wise attention mechanism that adaptively merges segmentation information with texture statistics to reconcile structural guiding with textural fidelity. A thorough comparative analysis was performed utilizing three internal variants—Vanilla GAN, Wasserstein GAN (WGAN), and WGAN-GP—against leading baselines, including TextureGAN and Pix2Pix. The assessment utilized a comprehensive multi-metric framework that included SSIM, FID, KID, LPIPS, and DISTS, in conjunction with a VGG-19 based perceptual loss. Experimental results indicate a notable divergence between pixel-wise accuracy and perceptual realism; although established baselines attained elevated PSNR values, the suggested Vanilla GAN and WGAN models exhibited enhanced perceptual fidelity, achieving the lowest LPIPS and DISTS scores. The WGAN-GP model, although theoretically stable, produced smoother but less complex textures due to the regularization enforced by the gradient penalty term. Ablation investigations further validated that the attention mechanism consistently enhanced structural alignment and texture sharpness across all topologies. Thus, the study suggests that Vanilla GAN and WGAN architectures, enhanced by attention-based fusion, offer an optimal balance between realism and structural fidelity for high-frequency texture creation applications.Keywords
This publication has 24 references indexed in Scilit:
- Research on predicting building façade deterioration in winter cities using diffusion modelJournal of Building Engineering, 2025
- A framework for fully automated reconstruction of semantic building model at urban-scale using textured LoD2 dataISPRS Journal of Photogrammetry and Remote Sensing, 2024
- ALADA: A lite automatic data augmentation framework for industrial defect detectionAdvanced Engineering Informatics, 2023
- Procedural generation of semantically plausible small-scale townsGraphical Models, 2023
- Texture Analysis and Its Applications in Biomedical Imaging: A SurveyIEEE Reviews in Biomedical Engineering, 2021
- Adaptive Convolutions for Structure-Aware Style Transfer2021
- Visual-PSNR measure of image qualityJournal of Visual Communication and Image Representation, 2014
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Texture features for browsing and retrieval of image dataIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996
- Use of Ranks in One-Criterion Variance AnalysisJournal of the American Statistical Association, 1952