Multi-Reference Geometric Risk and Sparse Depth Refinement for Streaming 3D Reconstruction
Sensors · 05.11.2026 · 26 (21) · 6995
DOI: 10.3390/s26216995 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 05.11.2026. Verfasst von Chunguang Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical Engineering, Tianjin Sino-German University of Applied Sciences, Tianjin 300350, China. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Tianjin Municipal Education Commission.
Abstract (Originalsprache)
Streaming feed-forward 3D reconstruction produces depth predictions at successive frames, but cross-view geometric consistency and local depth accuracy may vary. We present a training-free, output-level approach that combines Multi-Reference Geometric Risk assessment with global-referenced conservative sparse depth refinement, leaving the pretrained backbone, its predicted poses, and its streaming state unchanged. Risk derived from predicted depth, intrinsics, and poses achieves a median Spearman correlation of 0.635 with scale-aligned depth error across 11 public scenes and a correlation of 0.556 on the real-robot Sequence E. With matched 2% sparse depth anchors, local refinement reduces Sequence E held-out AbsRel by 40.69% relative to Sparse Global. Spatial refinement also improves mean held-out depth error in all 55 public scene–policy comparisons and all 200 predefined fixed-mask scene–policy–seed comparisons. Retrospective risk-based frame ranking provides diagnostic benefits under reference-scale normalization, but the observed allocation gains are protocol-dependent and do not establish consistent improvements under historical sparse-scale propagation or deployable online scheduling. In an independent Bonn Leica comparison using shared ground-truth camera poses, Spatial increases recall at a 5 cm threshold but has lower precision and F-score than Sparse Global. These findings establish the value of conservative sparse depth refinement and multi-reference risk as complementary geometric-quality evidence, while distinguishing depth accuracy from downstream 3D geometric performance.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Mechanical Engineering, Tianjin Sino-German University of Applied Sciences, Tianjin 300350, China.
- Institute of Robotics and Intelligent Equipment, Tianjin University of Technology and Education, Tianjin 300222, China.
Förderung
- Tianjin Municipal Education Commission
Zitieren
APA
Wang, C., Sun, W., Zheng, J., Ge, M., & Qi, Y. (2026). Multi-Reference Geometric Risk and Sparse Depth Refinement for Streaming 3D Reconstruction. Sensors, 26(21), 6995. https://doi.org/10.3390/s26216995
Vancouver
Wang C, Sun W, Zheng J, Ge M, Qi Y. Multi-Reference Geometric Risk and Sparse Depth Refinement for Streaming 3D Reconstruction. Sensors. 2026;26(21):6995. doi:10.3390/s26216995
BibTeX
@article{Wang2026,
author = {Wang, Chunguang and Sun, Wei and Zheng, Jianlong and Ge, Meijing and Qi, Yuming},
title = {Multi-Reference Geometric Risk and Sparse Depth Refinement for Streaming 3D Reconstruction},
journal = {Sensors},
year = {2026},
volume = {26},
number = {21},
pages = {6995},
doi = {10.3390/s26216995}
}
EUVIMED