Research map / 3D vision / Gaussian splatting
Evolving Semantic Propagation for Aerial Semantic 3D Gaussian Splatting
Zihan Gao, Lingling Li, Xu Liu, Fang Liu, Licheng Jiao, Puhua Chen, Wenping Ma, Shuyuan Yang
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 semantic propagation via pseudo-labels (ablation) | sparse supervision only · 3D-AS (average over test scenes) | mIoU: 33.4 -> 58.3 | Improved |
| add evolutionary search instead of random selection (ablation) | EvoPropGS · 3D-AS (average over test scenes) | mIoU: 52.6 -> 58.3 | Improved |
| add evolutionary search instead of feature averaging (ablation) | EvoPropGS · 3D-AS (average over test scenes) | mIoU: 56.4 -> 58.3 | Improved |
| add 3D fitness to 2D-only fitness (ablation) | EvoPropGS · 3D-AS (average over test scenes) | mIoU: 53.1 -> 58.3 | Improved |
| add 2D fitness to 3D-only fitness (ablation) | EvoPropGS · 3D-AS (average over test scenes) | mIoU: 56.2 -> 58.3 | Improved |
| add 2D fitness to 3D-only fitness (ablation) | EvoPropGS · 3D-AS (average over test scenes) | mAcc: 84.6 -> 86.6 | Improved |
| use flexible chromosome encoding instead of rigid encoding (ablation) | EvoPropGS · 3D-AS (average over test scenes) | mIoU: 50.9 -> 58.3 | Improved |
| use DINOv2 features instead of CLIP (ablation) | EvoPropGS · 3D-AS (average over test scenes) | mIoU: 33.1 -> 58.3 | Improved |
| use DINOv2 features instead of MAE (ablation) | EvoPropGS · 3D-AS (average over test scenes) | mIoU: 40.6 -> 58.3 | Improved |
| use EvoPropGS with sparse labels instead of Gaussian Grouping with dense labels | EvoPropGS · 3D-AS (average over test scenes) | mIoU: 37.2 -> 58.3 | Improved |
| use Semantic Gaussian with dense labels instead of EvoPropGS with sparse labels | EvoPropGS · 3D-AS (average over test scenes) | mIoU: 58.3 -> 61.4 | Hurt |
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 9 of 9 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
- SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting (NeurIPS 2025 · similarity 0.89)
- Bootstraping Clustering of Gaussians for View-consistent 3D Scene Understanding (AAAI 2025 · similarity 0.88)
- ReferSplat: Referring Segmentation in 3D Gaussian Splatting (ICML 2025 · similarity 0.88)
- FHGS: Feature-Homogenized Gaussian Splatting (NeurIPS 2025 · similarity 0.88)
- Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes (CVPR 2025 · similarity 0.87)
- Efficient Decoupled Feature 3D Gaussian Splatting via Hierarchical Compression (CVPR 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.
