Paper Overview
- Field: Computer Vision
- Authors: Zhipeng Zhong, Matthew Coombes, Cunjia Liu
- Published: 2026-11-03
- arXiv: 2611.05361
- Experiments on TartanAirV2 and TartanGround show that, compared with Poisson surface reconstruction (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.
- Applying the pipeline to the BotanicGarden dataset enables systematic comparison of depth estimation and 3D reconstruction methods:
- Feed-forward 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 are more prone to failure in challenging vegetated scenes.
Summary
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. The authors present a LiDAR-based 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, they introduce the LargeDepth-Gap Visibility Score (LDGVS) for point-wise visibility filtering and automatic scale selection in Hidden Point Removal (HPR).
Key Results
Original Abstract
> 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 LiDAR-based 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. Feed-forward 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.
---
*Auto-collected on 2026-11-05*