EUVIMEDEUVIMED entdecken
Crossref

CIRNet: Compact Iterative Refinement Network for Real-Time Stereo Matching

Haopeng Wang, Zhanhong Chen, Yu Zhang, Yanbiao Sun, Jigui Zhu

IEEE Robotics and Automation Letters · 2026-08 · 11 (8) · 9175-9182

DOI: 10.1109/lra.2026.3703239 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Robotics and Automation Letters, 2026-08. Verfasst von Haopeng Wang und 4 weiteren Autor:innen. Gefördert von: National Science and Technology Major Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Stereo matching is crucial for 3D perception in autonomous driving and generalist robotics. Recent advancements transitioned from cost volume method to iterative refinement approach, offering superior details and spatial consistency. However, iterative methods remain constrained by expensive matching encoding and numerous refinement iterations, limiting latency-sensitive practical application. To unleash the accuracy superiority of iterative paradigms in real-time systems, we present Compact Iterative Refinement Network (CIRNet). Specifically, we design Compact Correlation Encoding (CCE) to allocate essential matching evidence by functional attributes, constructing global geometric context at deep level and fine-grained local similarity at shallow level to reduce redundant computation and provide reliable coarse initialization. Meanwhile, we introduce Staged Iterative Refinement (SIR) using early coarse correction for large residuals and a lightweight shared operator for fine details, improving the accuracy-latency trade-off and reaching near-saturated accuracy at lower latency. Evaluations on SceneFlow and KITTI show CIRNet sets new state-of-the-art in balancing accuracy and efficiency. Furthermore, CIRNet exhibits robust cross-domain generalization on multiple real-world datasets and practical deployability on embedded edge platform.

Förderung

  • National Science and Technology Major Project

Zitieren

APA

Wang, H., Chen, Z., Zhang, Y., Sun, Y., & Zhu, J. (2026). CIRNet: Compact Iterative Refinement Network for Real-Time Stereo Matching. IEEE Robotics and Automation Letters, 11(8), 9175-9182. https://doi.org/10.1109/lra.2026.3703239

Vancouver

Wang H, Chen Z, Zhang Y, Sun Y, Zhu J. CIRNet: Compact Iterative Refinement Network for Real-Time Stereo Matching. IEEE Robotics and Automation Letters. 2026;11(8):9175-9182. doi:10.1109/lra.2026.3703239

BibTeX
@article{Wang2026,
  author = {Wang, Haopeng and Chen, Zhanhong and Zhang, Yu and Sun, Yanbiao and Zhu, Jigui},
  title = {CIRNet: Compact Iterative Refinement Network for Real-Time Stereo Matching},
  journal = {IEEE Robotics and Automation Letters},
  year = {2026},
  volume = {11},
  number = {8},
  pages = {9175--9182},
  doi = {10.1109/lra.2026.3703239}
}
Kostenlos starten →