EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CasFormer: A Cascaded Transformer Network with Self-Cross Attention for Forest Multi-View Reconstruction and Tree Parameter Extraction

Rong Zhao, Zhao Chen, Cairong Xu, Yingran Che, Ranping Xiong

Forests · 30.10.2026 · 17 (11) · 1305

DOI: 10.3390/f17111305 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Forests, online erschienen am 30.10.2026. Verfasst von Rong Zhao und 4 weiteren Autor:innen. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image-based forest 3D reconstruction from multi-view imagery can generate stand-level point clouds and provide data support for extracting individual-tree structural parameters, such as diameter at breast height (DBH) and tree height. Three-dimensional reconstruction of forest ecosystems is fundamental to forest resource monitoring and biomass assessment. However, forest scenes are characterized by frequent branch and leaf occlusions, repetitive bark and foliage textures, and complex illumination conditions. These factors often introduce ambiguities into feature matching and cost aggregation in convolutional neural network (CNN)-based multi-view stereo (MVS) methods, resulting in incomplete point clouds and depth estimation errors. To address these challenges, this study proposes CasFormer, a cascaded multi-view 3D reconstruction model designed for near-ground handheld forest imagery. Built upon a cascaded cost-volume framework, CasFormer constructs a Self-and-Cross Attention Feature Pyramid Network (SC-FPN) and incorporates a Positional Encoding Generator (PEG) to inject camera geometric priors into feature representations, thereby enhancing feature discriminability in repetitive weak-texture regions. In addition, a pixel-wise visibility-weighted cost volume is used to adaptively adjust source-view aggregation weights according to matching confidence, reducing the influence of occluded or low-quality source views on the cost volume and improving the stability of depth estimation in forest scenes. Experiments across three forest plots show that CasFormer achieves the highest overall single-tree matching rate (99.14%) and outperforms the competing methods in tree-height accuracy and point-cloud density at all three plots. Its mean DAE is 92.87%, exceeding FS-MVSNet and MVSFormer by 0.97 and 2.78 percentage points, respectively. CasFormer attains the lowest DBH RMSE at Plots 1 and 2; at Plot 3, its RMSE is comparable to those of MVSFormer and FS-MVSNet. Its point-cloud densities are 3.87, 2.17, and 4.87 × 106 points/m2 at Plots 1, 2, and 3, respectively, the highest among the methods evaluated at each plot. These results demonstrate that CasFormer improves plot-scale forest 3D reconstruction using handheld RGB imagery that can be acquired with minimal effort. It provides an effective image-based reconstruction method for extracting individual-tree parameters and supports sustainable smart forestry monitoring.

Förderung

  • National Key Research and Development Program of China

Zitieren

APA

Zhao, R., Chen, Z., Xu, C., Che, Y., & Xiong, R. (2026). CasFormer: A Cascaded Transformer Network with Self-Cross Attention for Forest Multi-View Reconstruction and Tree Parameter Extraction. Forests, 17(11), 1305. https://doi.org/10.3390/f17111305

Vancouver

Zhao R, Chen Z, Xu C, Che Y, Xiong R. CasFormer: A Cascaded Transformer Network with Self-Cross Attention for Forest Multi-View Reconstruction and Tree Parameter Extraction. Forests. 2026;17(11):1305. doi:10.3390/f17111305

BibTeX
@article{Zhao2026,
  author = {Zhao, Rong and Chen, Zhao and Xu, Cairong and Che, Yingran and Xiong, Ranping},
  title = {CasFormer: A Cascaded Transformer Network with Self-Cross Attention for Forest Multi-View Reconstruction and Tree Parameter Extraction},
  journal = {Forests},
  year = {2026},
  volume = {17},
  number = {11},
  pages = {1305},
  doi = {10.3390/f17111305}
}
Kostenlos starten →