Research map / 3D vision / Gaussian splatting
Space-Time Forecasting of Dynamic Scenes with Motion-aware Gaussian Grouping
Junmyeong Lee, Hoseung Choi, Minsu Cho
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 group-wise optimization and group-wise forecasting (ablation) | MoGaF · iPhone dataset tracking (forecast 40%) | 3D EPE: 0.296 -> 0.236 | Improved |
| add group-wise design (occlusion accuracy) (ablation) | MoGaF · iPhone dataset tracking (forecast 40%) | OA: 64.1 -> 80.1 | Improved |
| add group-wise design (2D delta_avg) (ablation) | MoGaF · iPhone dataset tracking (forecast 40%) | delta_avg: 8.5 -> 8.8 | Improved |
| add masked motion modeling to forecaster training (ablation) | MoGaF forecaster · D-NeRF (20% forecast) | PSNR: 24.68 -> 25.87 | Improved |
| add masked motion modeling (LPIPS) (ablation) | MoGaF forecaster · D-NeRF (20% forecast) | LPIPS: 0.0551 -> 0.0491 | Improved |
| MoGaF forecaster vs GSPred-SoM on iPhone (80% observed) | SoM-based 4DGS · iPhone dataset (80% observed) | mPSNR: 14.99 -> 15.58 | Improved |
| MoGaF vs GSPred-SoM on iPhone (80% observed) | SoM-based 4DGS · iPhone dataset (80% observed) | mSSIM: 0.6405 -> 0.6395 | No clear effect |
| MoGaF vs GSPred-SoM on iPhone (60% observed) | SoM-based 4DGS · iPhone dataset (60% observed) | mLPIPS: 0.4256 -> 0.4245 | No clear effect |
| MoGaF vs GSPred on D-NeRF (60% observed) | 4DGS · D-NeRF (60% observed) | PSNR: 21.78 -> 23.37 | Improved |
Closest papers by meaning
- Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis (CVPR 2024 · similarity 0.89)
- Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling (AAAI 2025 · similarity 0.88)
- FreeTimeGS: Free Gaussian Primitives at Anytime Anywhere for Dynamic Scene Reconstruction (CVPR 2025 · similarity 0.87)
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (ICLR 2024 · similarity 0.87)
- Fully Explicit Dynamic Gaussian Splatting (NeurIPS 2024 · similarity 0.87)
- Motion Decoupled 3D Gaussian Splatting for Dynamic Object Representation (AAAI 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.
