Metraipolis › archive › dc_cd2f8cbff298

Visibility-Aware Reference Generation for Benchmarking Visual 3D Reconstruction in Vegetation-Rich Environments — arXiv:2611.05361

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.05361
License (as archived): CC0-1.0
Archived: 2026-11-04T12:57:31.413Z
SHA-256 of the archived text: 6c934c6f3b14f682ac37febbdfc0bed281096c0984388d7e6291135cdbe01ad5
Stable URL of this page: https://metraipolis.com/documento/dc_cd2f8cbff298

How to cite

Visibility-Aware Reference Generation for Benchmarking Visual 3D Reconstruction in Vegetation-Rich Environments — arXiv:2611.05361 — arXiv (en), https://arxiv.org/abs/2611.05361 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd2f8cbff298 (Metraipolis archive dc_cd2f8cbff298, sha256 6c934c6f3b14f682ac37febbdfc0bed281096c0984388d7e6291135cdbe01ad5)

BibTeX

@misc{dccd2f8cbff298,
  title = {Visibility-Aware Reference Generation for Benchmarking Visual 3D Reconstruction in Vegetation-Rich Environments — arXiv:2611.05361},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05361},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd2f8cbff298; sha256 6c934c6f3b14f682ac37febbdfc0bed281096c0984388d7e6291135cdbe01ad5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05361. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reliable evaluation of visual 3D reconstruction and depth estimation in vegetation-rich outdoor environments is limited by the scarcity of geometric ground-truth data and the cost of complete scanner surveys. We present a LiDARbased reference-generation pipeline for evaluating the zero-shot performance of feed-forward visual-geometry models alongside conventional structure-from-motion (SfM) methods. The pipeline reuses camera images, LiDAR scans, and reference poses from existing multi-sensor localization datasets to generate per-view depth maps and visible reference point clouds. To address visibility errors in accumulated LiDAR scans, we introduce the LargeDepth-Gap Visibility Score (LDGVS) for point-wise visibility filtering and automatic scale selection in Hidden Point Removal(HPR). Experiments on TartanAirV2 and TartanGround show that, compared with Poisson surface reconstruction, which is an approach suited to completed scan surveys, the combined HPR and LDGVS filtering retains approximately three times the point density at comparable absolute relative error. We also apply the pipeline to the BotanicGarden dataset to systematically compare depth estimation and 3D reconstruction methods. Feedforward methods produce dense depth predictions efficiently, but their 3D reconstructions can contain duplicated structures. Conventional SfM generally produces more coherent geometry, but its reconstructions remain sparse and more prone to failure in challenging vegetated scenes. The benchmark toolkit and datasets will be released.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2611.05361 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-04T12:33:47.239Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).