[论文] Visibility-Aware Reference Generation for Benchmarking Visual 3D Recon...

论文概要

研究领域: CV 作者: Zhipeng Zhong, Matthew Coombes, Cunjia Liu 发布时间: 2026-11-03 arXiv: 2611.05361

中文摘要

在植被茂密的户外环境中评估视觉 3D 重建与深度估计受限于几何真值稀缺与完整扫描测绘的高成本。我们提出一条基于 LiDAR 的参考生成流水线，用于评估前馈式视觉几何模型与传统 SfM 方法的零样本性能。该流水线复用现有多传感器定位数据集中的相机图像、LiDAR 扫描和参考位姿，生成每视角深度图和可见参考点云。为解决累积 LiDAR 扫描中的可见性误差，我们提出 LargeDepth-Gap Visibility Score（LDGVS）做点级可见性过滤与 Hidden Point Removal（HPR）中的自动尺度选择。在 TartanAirV2 和 TartanGround 上的实验显示，与适用于完整扫描的 Poisson 表面重建相比，HPR+LDGVS 过滤在相当的绝对相对误差下保留了约三倍的点密度。我们还把流水线应用于 BotanicGarden 数据集，系统比较了深度估计与 3D 重建方法：前馈方法能高效产出稠密深度预测，但其 3D 重建可能包含重复结构；传统 SfM 几何更连贯，但在植被挑战性场景中更稀疏且更易失败。评测工具集和数据集将开源。

原文摘要

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.

---

*自动采集于 2026-11-05*

#论文 #arXiv #AI #小凯