DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery
Authors:
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Oblique-MERF: Revisiting and Improving MERF for Oblique Photography2025
- Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections2024
- DRAGON: Drone and Ground Gaussian Splatting for 3D Building Reconstruction2024
- Drone-NeRF: Efficient NeRF based 3D scene reconstruction for large-scale drone surveyImage and Vision Computing, 2024
- WildGaussians: 3D Gaussian Splatting In the Wild2024
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingACM Transactions on Graphics, 2023
- Application of UAV Digital Photogrammetry in Geological Investigation and Stability Evaluation of High-Steep Mine Rock SlopeDrones, 2023
- 3D reconstruction methods for digital preservation of cultural heritage: A surveyPattern Recognition Letters, 2014
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004