Research map / 3D vision / Gaussian splatting
Online Segment 3D Gaussians via Launching Virtual Drones
Liwei Liao, Rongjie Wang, Ronggang Wang
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 NBV virtual-drone views instead of using only real scene views (ablation) | SAGO · LERF-Mask | mIoU: 36.7 -> 91.0 | Improved |
| add NBV virtual-drone views instead of using only real scene views (ablation) | SAGO · NVOS | mIoU: 89.1 -> 92.7 | Improved |
| add NBV virtual-drone views instead of using only real scene views (ablation) | SAGO · SPIn-NeRF | mIoU: 90.1 -> 92.5 | Improved |
| use center-based MFF instead of splat-based MFF (ablation) | SAGO · SPIn-NeRF | mIoU: 91.1 -> 92.5 | Improved |
| use center-based MFF instead of splat-based MFF (ablation) | SAGO · NVOS | mIoU: 92.5 -> 92.7 | No clear effect |
| replace setup-based pipeline with online NBV planning (setup-free) | SAGO vs GaussianCut · NVOS | segmentation time: 40~60s -> 0.4~0.9s | Improved |
| setup-free online method versus offline SAGA with ~1h setup | SAGO · NVOS | mIoU: 92.6 -> 92.7 | Improved |
| setup-free online method versus offline SAGA | SAGO · SPIn-NeRF | mIoU: 93.4 -> 92.5 | Hurt |
Closest papers by meaning
- iSegMan: Interactive Segment-and-Manipulate 3D Gaussians (CVPR 2025 · similarity 0.89)
- GaussianCut: Interactive segmentation via graph cut for 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.89)
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.89)
- GaussianPro: 3D Gaussian Splatting with Progressive Propagation (ICML 2024 · similarity 0.88)
- SfM-Free 3D Gaussian Splatting via Hierarchical Training (CVPR 2025 · similarity 0.88)
- Steepest Descent Density Control for Compact 3D Gaussian Splatting (CVPR 2025 · similarity 0.88)
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.
