针对无人机拍摄的复杂场景，实现更鲁棒的3D重建。
DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery
- 通过自适应掩码阈值消除动态干扰物
- 在视点受限下仍能生成高质量3D图像
- 适合野外无人机3D建模任务
无人机因机动性强，已成为重建野外场景的重要工具。近年来辐射场方法在渲染质量上取得显著进展，为无人机影像3D重建提供了新路径。然而，野外环境中动态物体破坏了辐射场的静态场景假设，且视点受限难以准确捕捉场景几何结构。为此，我们提出DroneSplat，一种面向真实无人机影像的鲁棒3D重建框架。该方法结合局部-全局分割启发式与统计方法，自适应调整掩码阈值，精准识别并剔除静态场景中的动态干扰物。通过引入多视角立体匹配预测和体素引导优化策略，增强3D高斯溅射在视点受限下的表现，支持高质量渲染。我们构建了一个包含动态与静态场景的真实无人机采集3D重建数据集，用于全面评估。大量实验表明，DroneSplat在处理真实无人机影像方面优于3DGS与NeRF基线模型。
原文摘要 · Abstract (English)
Drones have become essential tools for reconstructing wild scenes due to their outstanding maneuverability. Recent advances in radiance field methods have achieved remarkable rendering quality, providing a new avenue for 3D reconstruction from drone imagery. However, dynamic distractors in wild environments challenge the static scene assumption in radiance fields, while limited view constraints hinder the accurate capture of underlying scene geometry. To address these challenges, we introduce DroneSplat, a novel framework designed for robust 3D reconstruction from in-the-wild drone imagery. Our method adaptively adjusts masking thresholds by integrating local-global segmentation heuristics with statistical approaches, enabling precise identification and elimination of dynamic distractors in static scenes. We enhance 3D Gaussian Splatting with multi-view stereo predictions and a voxel-guided optimization strategy, supporting high-quality rendering under limited view constraints. For comprehensive evaluation, we provide a drone-captured 3D reconstruction dataset encompassing both dynamic and static scenes. Extensive experiments demonstrate that DroneSplat outperforms both 3DGS and NeRF baselines in handling in-the-wild drone imagery.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。