May 4, 2024ISPRS Open Journal of Photogrammetry and Remote SensingOpen Access

Depth estimation and 3D reconstruction from UAV-borne imagery: Evaluation on the UseGeo dataset

View Full Paper

Ask AI

Bookmark

Authors

MHMario HermannKarlsruhe Institute of Technology MWMartin WeinmannKarlsruhe Institute of Technology FNFrancesco NexUniversity of Twente

Discussion

Member takes

Implication

Benchmark evaluation demonstrates distinct algorithmic performance variations across UAV aerial imagery, highlighting operational trade-offs for automated 3D reconstruction.

Key Points

COLMAP depth estimation outperforms competing approaches across aerial imagery, while ACMMP achieves the lowest error and highest completeness for reconstructed point clouds.
OpenMVS produces triangle meshes with the lowest overall error, whereas self-supervised single-image depth estimation attains the fastest frame rate despite higher errors.
Benchmark evaluation on the UseGeo dataset demonstrates specialized multi-view 3d reconstruction trade-offs, supporting standardized protocols for aerial survey modeling.

Cite This Study

Hermann et al. (2024) studied this question.

synapsesocial.com/papers/68e6b91fb6db643587639a1c https://doi.org/10.1016/j.ophoto.2024.100065

View Full Paper

Ask AI

Bookmark

Implication

Benchmark evaluation demonstrates distinct algorithmic performance variations across UAV aerial imagery, highlighting operational trade-offs for automated 3D reconstruction.

Depth estimation and 3D reconstruction from UAV-borne imagery: Evaluation on the UseGeo dataset

Discussion

Member takes

Implication

Key Points

Cite This Study

Depth estimation and 3D reconstruction from UAV-borne imagery: Evaluation on the UseGeo dataset

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider