发表机构
Stanford University（斯坦福大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究稀疏视图神经重建的单目深度监督，用Depth Anything V2作密集单目深度先验，经尺度变换拟合对齐预测，通过仅RGB基线模型生成的光度掩码选择性应用深度监督，在不同场景评估，结果表明应选择性适度加权应用。
AI 中文摘要
稀疏视图神经重建在户外驾驶场景具有挑战性，单目深度估计器预测有噪声。本文研究稀疏视图神经重建的单目深度监督，用Depth Anything V2作密集单目深度先验，经尺度变换拟合对齐预测，通过仅RGB基线模型生成的光度掩码选择性应用深度监督。在两个场景表示上评估，结果表明单目深度先验对稀疏视图重建有用，但应选择性适度加权应用。
英文摘要
Sparse-view neural reconstruction in outdoor driving is challenging due to narrow forward-facing trajectories and limited multi-view overlap, and monocular depth priors, though dense, are noisy and not uniformly reliable. We use Depth Anything V2 (DA-V2) as a dense monocular depth prior, align its per-image scale and shift to metric depth using sparse anchors (LiDAR and COLMAP) and apply depth supervision selectively through photometric masks generated from an RGB-only baseline model, and evaluate on Mip-NeRF-360 and Splatfacto. On KITTISeq02, masked depth supervision gives only marginal gains for Mip-NeRF-360 and does not improve geometry. In contrast, Splatfacto benefits clearly, improving PSNR from 14.903 to 15.932 and reducing RMSE from 0.542 to 0.100. Against global supervision, the proposed mask achieves 0.44-0.70,dB PSNR gains across KITTI sequences 00/02/05 at tied or better RMSE, while yielding no change on Mip-NeRF-360. This indicates the mask primarily enhances rendering fidelity rather than geometry. Matched-ratio ablations and two further KITTI fragments confirm the gains come from selecting reliable low-error regions, rather than from fewer pixels. On the Bicycle scene, depth supervision improves geometry but hurts RGB rendering quality when multi-view coverage is already strong. Using DA-V2 as a representative prior, results suggest that monocular depth priors are valuable for under-constrained sparse-view reconstruction when applied selectively with moderate weighting.
Comments9 pages, 6 figures. All authors contributed equally
