Research map / 3D vision / Gaussian splatting
CaT-GS: Efficient 3DGS Rendering for Large-Scale Scenes with Inter-frame Caching and Tile Scheduling
Tingjia Zhang, Bo Chen, Shengzhong Liu, Fan Wu, Guihai Chen
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 inter-frame caching with speculative pre-processing (ablation) | CaT-GS · UAV-1 | average FPS: 155.3 -> 241.5 | Improved |
| add inter-frame caching with speculative pre-processing (ablation) | CaT-GS · Truck | average FPS: 494.4 -> 736.5 | Improved |
| add load-aware task splitting and split kernel (ablation) | CaT-GS · Playroom | average FPS: 840.6 -> 922.3 | Improved |
| add load-aware task splitting and split kernel (ablation) | CaT-GS · UAV-1 | average FPS: 210.3 -> 241.5 | Improved |
| render sub-frames from cached key-frame lists | CaT-GS · Truck | PSNR: 28.19 -> 28.16 | Hurt |
| render sub-frames from cached key-frame lists | CaT-GS · UAV-1 | SSIM: 0.931 -> 0.926 | Hurt |
| retrain model with tile-aware constraint loss | ADR-GS · Truck | PSNR: 28.21 -> 26.50 | Hurt |
| use speculative multi-frame list instead of per-frame intersection | CaT-GS key frames · Garden | render list length: 6,682 -> 7,032 | Hurt |
| use CaT-GS instead of FlashGS on larger scenes | CaT-GS · UAV scenes | average FPS: over 60% improvement, up to over 80% | Improved |
Closest papers by meaning
- FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering (CVPR 2025 · similarity 0.92)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.92)
- On Scaling Up 3D Gaussian Splatting Training (ICLR 2025 · similarity 0.91)
- DashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds (CVPR 2025 · similarity 0.91)
- PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting (CVPR 2025 · similarity 0.91)
- Steepest Descent Density Control for Compact 3D Gaussian Splatting (CVPR 2025 · similarity 0.91)
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.
