DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery
Jiadong Tang, Yu Gao, Dianyi Yang, Liqi Yan, Yufeng Yue, Yi Yang
Abstract
Figure 1 . Given a set of drone imagery, our method effectively eliminates the impact of dynamic distractors on the static scenes (e.g., vehicles driving on the road). The right side of the figure shows the rendering results of our method compared to 3DGS under input view and novel view. Our method eliminates distractors while 3DGS generates artifacts in the corresponding regions. Moreover, our method reconstructs scenes with accurate geometry under limited viewpoints, demonstrating robustness to significant view variation (novel view).
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 2fc76645-0cba-4bbe-9993-49f3c492a0d1Cited by top-tier papers6
- AeroDGS: Physically Consistent Dynamic Gaussian Splatting for Single-Sequence Aerial 4D ReconstructionHanyang Liu, Rongjun QinCVPR 2026 · 2 citations
- DualSplat: Robust 3D Gaussian Splatting via Pseudo-Mask Bootstrapping from Reconstruction FailuresXu Wang, Zhiru Wang, Shiyun Xie, Chengwei Pan et al.CVPR 2026 · 1 citation
- FilterGS: Traversal-Free Parallel Filtering and Adaptive Shrinking for Large-Scale LoD 3D Gaussian SplattingYixian Wang, Haolin Yu, Jiadong Tang, Yu Gao et al.CVPR 2026 · 1 citation
- AeroGS: Scale-Aware Gaussian Splatting for Pose-Free Dynamic UAV Scene ReconstructionTingyun Li, Xinyi Liu, Yongjun Zhang, Yi Wan et al.CVPR 2026
- Energy-GS: Image Energy-guided Pose Alignment Gaussian Splatting with redesigned pose gradient flowYu Gao, Lutong Su, Ruixiang Huang, Tianji Jiang et al.CVPR 2026
Builds on27
- Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao et al.ICCV 2023 · 13,211 citations
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
- Depth-supervised NeRF: Fewer Views and Faster Training for FreeKangle Deng, Andrew Liu, Jun-Yan Zhu, Deva RamananCVPR 2022 · 756 citations
- Block-NeRF: Scalable Large Scene Neural View SynthesisMatthew Tancik, Vincent Casser, Xinchen Yan, Sabeek Pradhan et al.CVPR 2022 · 702 citations
- RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse InputsMichael Niemeyer, Jonathan T. Barron, Ben Mildenhall, Mehdi S. M. Sajjadi et al.CVPR 2022 · 513 citations
Related papers
- WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic EnvironmentsJianhao Zheng, Zihan Zhu, Valentin Bieri, Marc Pollefeys et al.CVPR 2025
- Distractor-free Generalizable 3D Gaussian SplattingYanqi Bao, Jing Liao, Jing Huo, Yang GaoICLR 2026 · 9 citations
- RobustNeRF: Ignoring Distractors with Robust LossesSara Sabour, Suhani Vora, Daniel Duckworth, Ivan Krasin et al.CVPR 2023
- DeSplat: Decomposed Gaussian Splatting for Distractor-Free RenderingYihao Wang, Marcus Klasson, Matias Turkulainen, Shuzhe Wang et al.CVPR 2025
- Modeling and Identifying Distractors with Curriculum for Robust 3D Gaussian SplattingRuiqi Li, Yiu-ming CheungACM MM 2025 · 1 citation
