ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo Matching
Journal of Imaging · 24.06.2026 · 12 (7) · 277
DOI: 10.3390/jimaging12070277 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 24.06.2026. Verfasst von Mahmoud Tahmasebi und 3 weiteren Autor:innen. Beteiligte Einrichtung: Center for Mathematical Modelling and Intelligent Systems for Health and Environment (MISHE), Atlantic Technological University, F91 YW50 Sligo, Irel…. Die Arbeit nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Atlantic Technological University President's Bursary, Atlantic Technological University.
Abstract (Originalsprache)
Stereo matching has become an increasingly important component of modern autonomous systems. Developing deep learning-based stereo-matching models that deliver high accuracy while operating in real time continues to be a major challenge in computer vision. In the domain of cost volume-based stereo matching, accurate disparity estimation depends heavily on large-scale cost volumes. However, such large volumes store substantial redundant information and also require computationally intensive aggregation units for processing and regression, making real-time performance unattainable. Conversely, small-scale cost volumes followed by lightweight aggregation units provide a promising route for real-time performance, but lack sufficient information to ensure highly accurate disparity estimation. To address this challenge, we propose the Enhanced Shuffle Mixer (ESM) to mitigate information loss associated with small-scale cost volumes. ESM restores critical details by integrating primary features into the disparity upsampling unit. It quickly extracts features from the initial disparity estimation and fuses them with image features. These features are mixed by shuffling and layer splitting, then refined through a compact feature-guided hourglass network to recover more detailed scene geometry. The ESM focuses on local contextual connectivity with a large receptive field and low computational cost, leading to improved disparity estimation accuracy while maintaining real-time performance under the evaluated settings. The compact version of ESMStereo achieves an inference speed of 116 FPS on RTX 4070S and 91 FPS on the AGX Orin.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Center for Mathematical Modelling and Intelligent Systems for Health and Environment (MISHE), Atlantic Technological University, F91 YW50 Sligo, Ireland.
- Department of Engineering and Physics, Bridgewater College, Bridgewater, VA 22812-1599, USA.
- Center for Mathematical Modelling and Intelligent Systems for Health and Environment (MISHE), Atlantic Technological University, F92 FC93 Donegal, Ireland.
ORCID-Profile: Mahmoud Tahmasebi, Kevin Meehan, Marion McAfee
Förderung
- Atlantic Technological University President's Bursary
- Atlantic Technological University
Zitieren
APA
Tahmasebi, M., Huq, S., Meehan, K., & McAfee, M. (2026). ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo Matching. Journal of Imaging, 12(7), 277. https://doi.org/10.3390/jimaging12070277
Vancouver
Tahmasebi M, Huq S, Meehan K, McAfee M. ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo Matching. Journal of Imaging. 2026;12(7):277. doi:10.3390/jimaging12070277
BibTeX
@article{Tahmasebi2026,
author = {Tahmasebi, Mahmoud and Huq, Saif and Meehan, Kevin and McAfee, Marion},
title = {ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo Matching},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {7},
pages = {277},
doi = {10.3390/jimaging12070277}
}
EUVIMED