EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Object-Aware Computational Integral Imaging for Improved Object Depth Estimation and Stereo Matching Training

Daniel Vais iD, Yitzhak Yitzhaky iD

Sensors · 01.07.2026 · 26 (13) · 4149

DOI: 10.3390/s26134149 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 01.07.2026. Verfasst von Daniel Vais und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electro-Optics and Photonics Engineering, School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer Sheva…. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Israel Science Foundation, Israel Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Depth estimation is an active area of research in computer vision. When restricted to passive imaging, it is frequently approached as a stereo matching problem. Due to significant advancements in deep learning, stereo matching models have seen substantial development. Most stereo matching models utilize supervised learning, relying on disparity maps as ground truth, typically obtained via active imaging systems. In this work, we introduce a passive multi-view framework for generating ground-truth depth data for stereo matching models using Computational Integral Imaging (CII). Using CII, we extract object depths from multi-view images obtained via a passive camera array and use these depths as training targets, eliminating the need for active depth acquisition. To improve the robustness and accuracy of CII-based depth extraction, we propose an object-aware formulation that incorporates pretrained object segmentation into the depth extraction process. This enables more reliable depth estimation for objects with complex appearances and challenging scene contexts such as occlusions. Furthermore, we exploit the camera array as a multi-stereo acquisition system, generating diverse stereo pairs with varying baselines and viewing orientations. The resulting training data expose stereo matching models to a broader range of geometric configurations than conventional stereo datasets. Our results demonstrate that this approach enhances the generalization capabilities of stereo matching models.

Schlagwörter

Stichwörter der Autor:innen

ROIcomputational integral imaging (CII)depth estimationdisparityobject detectionsegmentationstereo matching

Autor:innen und Institutionen

  • Department of Electro-Optics and Photonics Engineering, School of Electrical and Computer Engineering, Ben-Gurion University of the Negev, Beer Sheva 84105, Israel.

ORCID-Profile: Daniel Vais, Yitzhak Yitzhaky

Förderung

  • The Israel Science Foundation
  • Israel Science Foundation

Zitieren

APA

Vais, D., & Yitzhaky, Y. (2026). Object-Aware Computational Integral Imaging for Improved Object Depth Estimation and Stereo Matching Training. Sensors, 26(13), 4149. https://doi.org/10.3390/s26134149

Vancouver

Vais D, Yitzhaky Y. Object-Aware Computational Integral Imaging for Improved Object Depth Estimation and Stereo Matching Training. Sensors. 2026;26(13):4149. doi:10.3390/s26134149

BibTeX
@article{Vais2026,
  author = {Vais, Daniel and Yitzhaky, Yitzhak},
  title = {Object-Aware Computational Integral Imaging for Improved Object Depth Estimation and Stereo Matching Training},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {13},
  pages = {4149},
  doi = {10.3390/s26134149}
}
Kostenlos starten →