EUVIMEDEUVIMED entdecken
Crossref

Teacher–student-paradigm-based 3D range-gated imaging method: exploiting depth cues from pre-trained large RGB depth estimation models

Jinming Gao, Xiaoquan Liu, Di Zhang, Yunpeng Li, Deng Chen, Xinwei Wang

Photonics Research · 01.03.2026 · 14 (3) · 885

DOI: 10.1364/prj.574911 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Photonics Research, online erschienen am 27.02.2026. Verfasst von Jinming Gao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hubei Province, Science Foundation Research Project of Wuhan Institute of Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

3D range-gated imaging (3DRGI) has great potential for long-range detection in adverse weather and nighttime low-light conditions, though existing methods are limited by the inherent flaws of gated images, such as a lack of color and susceptibility to specular noise, which degrades depth accuracy. Concurrently, large depth estimation models with millions of parameters, trained on large-scale RGB images have demonstrated powerful generalization for depth estimation. To bridge this gap, we propose a teacher–student paradigm that transfers robust relative depth knowledge from a pre-trained large RGB depth model (teacher) to a 3DRGI model (student). We first fine-tune the teacher model and distill its scene-level understanding using a relative-to-metric depth conversion strategy. Then, we introduce relative depth and edge consistency losses to guide our student model’s training, ensuring that its predictions remain aligned with the teacher’s strong priors. To further enhance depth quality and mitigate overfitting to sparse LiDAR features, we also propose a center-jitter cropping strategy. Extensive experiments and ablation studies validate our approach, demonstrating that it achieves state-of-the-art performance with comprehensive improvements across accuracy, visual quality, and computational efficiency. This cross-modal guidance paradigm highlights a promising direction for enhancing perception systems by leveraging large-scale models across different sensor domains.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Hubei Province
  • Science Foundation Research Project of Wuhan Institute of Technology

Zitieren

APA

Gao, J., Liu, X., Zhang, D., Li, Y., Chen, D., & Wang, X. (2026). Teacher–student-paradigm-based 3D range-gated imaging method: exploiting depth cues from pre-trained large RGB depth estimation models. Photonics Research, 14(3), 885. https://doi.org/10.1364/prj.574911

Vancouver

Gao J, Liu X, Zhang D, Li Y, Chen D, Wang X. Teacher–student-paradigm-based 3D range-gated imaging method: exploiting depth cues from pre-trained large RGB depth estimation models. Photonics Research. 2026;14(3):885. doi:10.1364/prj.574911

BibTeX
@article{Gao2026,
  author = {Gao, Jinming and Liu, Xiaoquan and Zhang, Di and Li, Yunpeng and Chen, Deng and Wang, Xinwei},
  title = {Teacher–student-paradigm-based 3D range-gated imaging method: exploiting depth cues from pre-trained large RGB depth estimation models},
  journal = {Photonics Research},
  year = {2026},
  volume = {14},
  number = {3},
  pages = {885},
  doi = {10.1364/prj.574911}
}
Kostenlos starten →