EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Structure-Prior-Guided Multi-Stage Cross-Modal Collaborative Network for RGB-D Semantic Segmentation

Yifan Yu iD, Zhiwei Zhong iD, Fan Min iD, Song Deng iD

Journal of Imaging · 20.08.2026 · 12 (8) · 394

DOI: 10.3390/jimaging12080394 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 20.08.2026. Verfasst von Yifan Yu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Software Engineering, Southwest Petroleum University, Chengdu 610500, China. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Red–green–blue and depth (RGB-D) semantic segmentation combines appearance cues from RGB images with geometric information from depth maps, but sensor noise, missing measurements, and boundary-inconsistent depth responses can introduce conflicting evidence during cross-modal fusion. We propose the Structure-Prior-Guided Network (SPGNet), a dual-branch, multi-stage framework that follows a correction-before-fusion strategy. At each feature scale, SPGNet estimates a learned structure prior from cross-modal agreement and discrepancy. The Cross-Modal Correction Module (CCM) uses this prior to regulate bidirectional information transfer, suppressing unreliable responses while retaining complementary cues. The Dual-branch Enhancement Fusion Module (DEF) then enhances the corrected RGB and depth features and integrates them through shared-representation-guided interaction, after which a lightweight multi-scale decoder produces the segmentation output. Under a unified training and evaluation protocol, SPGNet achieved three-run mean Intersection over Union (mIoU) scores of 50.845% on NYU Depth V2 and 48.457% on SUN RGB-D. Compared with the best reproduced baseline on each dataset, SPGNet improved mean mIoU by 2.111 and 0.899 percentage points, respectively. These results suggest that separating reliability-oriented correction from multimodal fusion can limit the propagation of unreliable cross-modal responses and improve indoor RGB-D semantic segmentation performance.

Schlagwörter

Stichwörter der Autor:innen

cross-modal correctiondepth reliabilitymulti-scale fusionred–green–blue and depth (RGB-D) semantic segmentationstructure prior

Autor:innen und Institutionen

  • School of Computer Science and Software Engineering, Southwest Petroleum University, Chengdu 610500, China.

ORCID-Profile: Yifan Yu, Zhiwei Zhong, Fan Min, Song Deng

Zitieren

APA

Yu, Y., Zhong, Z., Min, F., & Deng, S. (2026). Structure-Prior-Guided Multi-Stage Cross-Modal Collaborative Network for RGB-D Semantic Segmentation. Journal of Imaging, 12(8), 394. https://doi.org/10.3390/jimaging12080394

Vancouver

Yu Y, Zhong Z, Min F, Deng S. Structure-Prior-Guided Multi-Stage Cross-Modal Collaborative Network for RGB-D Semantic Segmentation. Journal of Imaging. 2026;12(8):394. doi:10.3390/jimaging12080394

BibTeX
@article{Yu2026,
  author = {Yu, Yifan and Zhong, Zhiwei and Min, Fan and Deng, Song},
  title = {Structure-Prior-Guided Multi-Stage Cross-Modal Collaborative Network for RGB-D Semantic Segmentation},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {8},
  pages = {394},
  doi = {10.3390/jimaging12080394}
}
Kostenlos starten →