Research map / 3D vision / Gaussian splatting
AeroGS: Scale-Aware Gaussian Splatting for Pose-Free Dynamic UAV Scene Reconstruction
Tingyun Li, Xinyi Liu, Yongjun Zhang, Yi Wan, Xiaoan Liu, Weiwei Fan, Jiahao Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Lmotion regularization on dynamic anchors (ablation) | AeroGS · Au-air | PSNR: 28.14 -> 30.21 | Improved |
| add entropy regularization on static confidence (ablation) | AeroGS · Au-air | PSNR: 30.21 -> 30.83 | Improved |
| add sparsity loss on dynamic anchors (ablation) | AeroGS · Au-air | PSNR: 30.83 -> 31.35 | Improved |
| add Ego-Object motion decoupling (ablation) | AeroGS · UAVDT | PSNR: 24.59 -> 26.16 | Improved |
| add HSTD module (appearance-deformation decoupling) (ablation) | AeroGS · UAVDT | PSNR: 26.16 -> 27.37 | Improved |
| add scale-complexity decoupling (ablation) | AeroGS · UAVDT | PSNR: 27.37 -> 27.77 | Improved |
| jointly optimize poses and dynamics instead of combining CF-3DGS poses with 4DGS | pose-free dynamic reconstruction · KITTI Odometry | PSNR: 19.03 -> 26.10 | Improved |
| AeroGS versus LongSplat for pose estimation | AeroGS · KITTI Odometry | ATE: 0.014 -> 0.006 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- DeSiRe-GS — DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes (CVPR 2025) · better on 4 of 4 shared results
- LongSplat — LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos (ICCV 2025) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.88)
- DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery (CVPR 2025 · similarity 0.88)
- DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos (NeurIPS 2025 · similarity 0.88)
- SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video (CVPR 2025 · similarity 0.88)
- Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes (CVPR 2025 · similarity 0.87)
- ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
