EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Lightweight Spatial-Frequency Collaborative Interaction Network for RGB-D Salient Object Detection

Yitong Lu iD, Ziguan Cui iD

Sensors · 10.06.2026 · 26 (12) · 3708

DOI: 10.3390/s26123708 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.06.2026. Verfasst von Yitong Lu und 1 weiteren Autor:innen. Beteiligte Einrichtung: Portland Institute, Nanjing University of Posts and Telecommunications, Nanjing 210023, China. Die Arbeit nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Nanjing University of Posts and Telecommunications.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

RGB-D salient object detection (SOD) aims to segment the most prominent objects from the background with a pair of given RGB and depth images. Existing RGB-D methods usually rely on heavy backbones to achieve high accuracy, while current lightweight methods struggle to maintain competitive performance. To break this intractable trade-off between effectiveness and model complexity, we propose a Lightweight Spatial-Frequency Collaborative Interaction Network (SFCINet), a unified and highly efficient framework. The core of SFCINet resides in the synergy between spatial-domain features and frequency-domain global priors. Specifically, we introduce the Spatial-Frequency Synergy (SFS) module, which shifts the perspective to a joint complex Fourier domain. By adaptively learning and optimizing the decoupled amplitude and phase components, it effectively isolates clutter to yield a purified global frequency-synergized prior, which modulates the spatial branches to eliminate cross-modal discrepancies for subsequent feature fusion while supplementing global information during decoding. To alleviate the interference caused by cross-modal representation discrepancies, we design the Cross-Guidance Interaction (CMGI) module, which employs a reciprocal anchoring mechanism. It guides the counterpart to mutually filter irrelevant noise and select task-relevant information, achieving fusion in an efficient manner. Finally, we present a Calibrated Hierarchical Decoder (CHD), which injects frequency-synergized global priors into the hierarchical decoding process. It re-establishes the connection between the frequency and spatial domains, ultimately achieving global-local consistency. Extensive experiments demonstrate that SFCINet delivers superior performance over state-of-the-art methods.

Schlagwörter

Stichwörter der Autor:innen

RGB-D imagesfrequency domainlightweightsalient object detection

Autor:innen und Institutionen

  • Portland Institute, Nanjing University of Posts and Telecommunications, Nanjing 210023, China.
  • College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China.

ORCID-Profile: Yitong Lu, Ziguan Cui

Förderung

  • Nanjing University of Posts and Telecommunications

Zitieren

APA

Lu, Y., & Cui, Z. (2026). Lightweight Spatial-Frequency Collaborative Interaction Network for RGB-D Salient Object Detection. Sensors, 26(12), 3708. https://doi.org/10.3390/s26123708

Vancouver

Lu Y, Cui Z. Lightweight Spatial-Frequency Collaborative Interaction Network for RGB-D Salient Object Detection. Sensors. 2026;26(12):3708. doi:10.3390/s26123708

BibTeX
@article{Lu2026,
  author = {Lu, Yitong and Cui, Ziguan},
  title = {Lightweight Spatial-Frequency Collaborative Interaction Network for RGB-D Salient Object Detection},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {12},
  pages = {3708},
  doi = {10.3390/s26123708}
}
Kostenlos starten →