VMI‐Stereo:Variational Bayesian Inference Based Multivariate Information Fusion Stereo Matching Network
IET Image Processing · 2026-01 · 20 (1)
DOI: 10.1049/ipr2.70386 ↗Kurz gefasst
Fachartikel in der Zeitschrift IET Image Processing, online erschienen am 13.05.2026. Verfasst von Jianchuan Zhao und 7 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
State‐of‐the‐art stereo matching models perform well on specific datasets, but data uncertainty limits their stability in unknown scenarios. In this paper, we propose VMI‐Stereo, a variational Bayesian inference based multivariate information fusion network, to enhance robustness and generalization. It designs a variational Bayesian approach for feature extraction and cost aggregation to data uncertainty and improve generalization to distribution shifts. Then, we introduce Fourier gradient perturbations to capture edge and texture information, strengthening uncertainty characterization. These advantages are integrated via the Fourier gradient perturbation volume, which fuses Fourier gradient and variational Bayesian features to enhance generalization to data uncertainty. Experiments show that trained on Scene Flow, our model reduces EPE by 8.38% over the baseline and achieves superior generalization on KITTI and ETH3D. These results confirm that VMI‐Stereo has significant advantages in handling stereo matching tasks in complex, uncertain environments.
Zitieren
APA
Zhao, J., Yang, W., Zhao, Y., Sang, H., Huang, L., Chen, Z., Li, J., & Qiu, W. (2026). VMI‐Stereo:Variational Bayesian Inference Based Multivariate Information Fusion Stereo Matching Network. IET Image Processing, 20(1). https://doi.org/10.1049/ipr2.70386
Vancouver
Zhao J, Yang W, Zhao Y, Sang H, Huang L, Chen Z, et al. VMI‐Stereo:Variational Bayesian Inference Based Multivariate Information Fusion Stereo Matching Network. IET Image Processing. 2026;20(1). doi:10.1049/ipr2.70386
BibTeX
@article{Zhao2026,
author = {Zhao, Jianchuan and Yang, Wenbang and Zhao, Yong and Sang, Haiwei and Huang, Lu and Chen, Ziyang and Li, Jianhua and Qiu, Wenfeng},
title = {VMI‐Stereo:Variational Bayesian Inference Based Multivariate Information Fusion Stereo Matching Network},
journal = {IET Image Processing},
year = {2026},
volume = {20},
number = {1},
doi = {10.1049/ipr2.70386}
}
EUVIMED