Research map / 3D vision / 3D generation
ID-Splat: Propagating Object Identities for Segmenting 3D Aerial-view Scenes
Yijing Wang, Xu Tang, Xiangrong Zhang, Jingjing Ma
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 Object Integration & Propagation guided by Mask-object Tracking (ablation) | ID-Splat (Occam's LGS base) · 3D-AS mean (3-view GT) | mIoU: 65.1 -> 66.1 | Improved |
| add Edge Object Propagation Strategy (EOPS) (ablation) | ID-Splat (Occam's LGS base) · 3D-AS mean (3-view GT) | mIoU: 66.1 -> 66.6 | Improved |
| add Multi-reference Semantic Propagation Strategy (MSPS) (ablation) | ID-Splat (Occam's LGS base) · 3D-AS mean (3-view GT) | mIoU: 66.6 -> 66.8 | Improved |
| add Object Integration & Propagation (ablation) | ID-Splat (Occam's LGS base) · 3D-AS mean (sparse single-view GT) | mIoU: 52.4 -> 57.6 | Improved |
| add full ID-Splat components (Net-4 vs Net-1) (ablation) | ID-Splat (Occam's LGS base) · 3D-AS mean (sparse single-view GT) | mIoU: 52.4 -> 58.4 | Improved |
| use larger SAM scale (Large vs Default) (ablation) | ID-Splat (Occam's LGS base) · 3D-AS mean (SAM scale) | mIoU: 66.8 -> 66.5 | Hurt |
| use Small SAM scale vs Default (ablation) | ID-Splat (Occam's LGS base) · 3D-AS mean (SAM scale) | mAcc: 89.9 -> 89.6 | Hurt |
| ID-Splat vs Semantic 3DGS | ID-Splat (Occam's LGS base) · 3D-AS Port Scene 2 | mIoU: 50.6 -> 51.9 | Improved |
| ID-Splat vs Semantic 3DGS | ID-Splat (Occam's LGS base) · 3D-AS City Scene 2 | mIoU: 59.3 -> 63.6 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Gaussian Grouping — Gaussian Grouping: Segment and Edit Anything in 3D Scenes (ECCV 2024) · 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
- Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding (AAAI 2025 · similarity 0.86)
- Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes (CVPR 2025 · similarity 0.86)
- Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans (CVPR 2024 · similarity 0.86)
- Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting (NeurIPS 2025 · similarity 0.85)
- Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery (CVPR 2024 · similarity 0.85)
- USCILab3D: A Large-scale, Long-term, Semantically Annotated Outdoor Dataset (NeurIPS 2024 · similarity 0.85)
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.
