Research map / 3D vision / Gaussian splatting
TileGS: Adaptive Gaussian Densification Through Tile-Guided Perceptual Analysis
Yiwen Wang, Ran Yi, Lizhuang 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 Tile-Guided Densification (TGD) (ablation) | Base 3DGS · Tanks and Temples | PSNR: 23.67 -> 24.10 | Improved |
| add Tile-Guided Densification (TGD) (ablation) | Base 3DGS · Tanks and Temples | LPIPS: 0.178 -> 0.159 | Improved |
| add Tile-Guided Densification (TGD) (ablation) | Base 3DGS · Tanks and Temples | memory: 438MB -> 364MB | Improved |
| add Tile-Level Structural Loss (TSL) (ablation) | Base 3DGS · Tanks and Temples | PSNR: 23.67 -> 23.74 | Improved |
| add Tile-Level Structural Loss (TSL) (ablation) | Base 3DGS · Tanks and Temples | memory: 438MB -> 278MB | Improved |
| add both TGD and TSL (ablation) | Base 3DGS · Tanks and Temples | PSNR: 23.67 -> 24.33 | Improved |
| plug TileGS into PixelGS | PixelGS · Deep Blending | memory: 1075 -> 578 | Improved |
| plug TileGS into PixelGS | PixelGS · Deep Blending | PSNR: 28.85 -> 29.27 | Improved |
| plug TileGS into AbsGS | AbsGS · Deep Blending | PSNR: 29.63 -> 29.66 | No clear effect |
| plug TileGS into mini-splatting-D | mini-splatting-D · Deep Blending | FPS: 163 -> 237 | Improved |
| increase tile size (ablation) | TileGS · Mip-NeRF 360 style scenes | LPIPS and model size | Mixed |
| use TileGS instead of 3DGS | 3DGS · Mip-NeRF 360 | memory: 734MB -> 422MB | Improved |
Closest papers by meaning
- Tile-wise vs. Image-wise: Random-Tile Loss and Training Paradigm for Gaussian Splatting (ICCV 2025 · similarity 0.92)
- Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting (ICML 2025 · similarity 0.92)
- EDGS: Eliminating Densification for Efficient Convergence of 3DGS (CVPR 2026 · similarity 0.92)
- Reframing Gaussian Splatting Densification with Complexity-Density Consistency of Primitives (NeurIPS 2025 · similarity 0.91)
- Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.91)
- IBGS: Image-Based Gaussian Splatting (NeurIPS 2025 · similarity 0.90)
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.
