Research map / 3D vision / Gaussian splatting
HUG: Hierarchical Urban Gaussian Splatting with Block-Based Reconstruction for Large-Scale Aerial Scenes
Mai Su, Zhongtao Wang, Huishan Au, Yilong Li, Xizhe Cao, Chengwei Pan, Yisong Chen, Guoping 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 visibility-based masking (C1) (ablation) | HUG baseline · Rubble | PSNR: 25.06 -> 25.40 | Improved |
| add hierarchical weighted image supervision (C2) (ablation) | HUG baseline + C1 · Rubble | PSNR: 25.40 -> 25.74 | Improved |
| add dynamic gradient thresholding (C3) (ablation) | HUG baseline + C1 + C2 · Rubble | PSNR: 25.74 -> 26.33 | Improved |
| add remaining components (anchor level transition, pruning, refiltering) to get full model (ablation) | HUG · Rubble | PSNR: 26.33 -> 26.42 | Improved |
| visibility-based partitioning instead of CityGS coarse-model partitioning | HUG · MatrixCity | partitioning time (min): 188 -> 1 | Improved |
| hierarchical neural Gaussian blocks (HUG) vs Octree-GS | HUG · MatrixCity | PSNR: 26.41 -> 28.02 | Improved |
| HUG vs Mega-NeRF on distant-view scene | HUG · Sci-Art | PSNR: 25.60 vs 21.83 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- MegaNeRF — Mega-NERF: Scalable Construction of Large-Scale NeRFs for Virtual Fly-Throughs (CVPR 2022) · better on 0 of 1 shared result
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
- Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes (CVPR 2025 · similarity 0.90)
- CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes (ICLR 2025 · similarity 0.90)
- EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis (CVPR 2025 · similarity 0.89)
- HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting (CVPR 2024 · similarity 0.89)
- DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus (NeurIPS 2024 · similarity 0.88)
- GaussianPro: 3D Gaussian Splatting with Progressive Propagation (ICML 2024 · 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.
