Research map / 3D vision / Gaussian splatting
Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering
Yurui Chen, Chun Gu, J H Jiang, Xiatian Zhu, Li Zhang
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 scene flow-based temporal smoothing (ablation) | PVG · Waymo dynamic NVS | PSNR: 26.50 -> 28.11 | Improved |
| add position-aware adaptive control (ablation) | PVG · Waymo dynamic NVS | PSNR: 27.90 -> 28.11 | Improved |
| add sky refinement (ablation) | PVG · Waymo dynamic NVS | PSNR: 28.01 -> 28.11 | Improved |
| add velocity loss (ablation) | PVG · Waymo dynamic NVS | PSNR: 28.04 -> 28.11 | Improved |
| add depth loss (ablation) | PVG · Waymo dynamic NVS | PSNR: 28.10 -> 28.11 | No clear effect |
| use sine vibration instead of constant position model (ablation) | PVG · Waymo dynamic NVS | PSNR: 27.77 -> 28.11 | Improved |
| use sine vibration instead of linear motion model (ablation) | PVG · Waymo dynamic NVS | PSNR: 27.09 -> 28.11 | Improved |
| vary vibration cycle l from 0.1 to 1.0 (ablation) | PVG · Waymo dynamic NVS | PSNR: 27.83 -> 28.11 -> 28.01 | Mixed |
| disable position-aware threshold r (infinite) (ablation) | PVG · Waymo dynamic NVS | PSNR: 27.90 -> 28.11 | Improved |
| lower eta from 0.50 to 0.25 (ablation) | PVG · Waymo dynamic NVS | PSNR: 28.11 -> 27.67 | Hurt |
| raise eta from 0.50 to 1.00 (ablation) | PVG · Waymo dynamic image reconstruction | PSNR: 32.46 -> 32.27 | Hurt |
| PVG vs box-based OmniRe | PVG · Waymo 12 scenes NVS | PSNR: 29.41 -> 30.95 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- EmerNeRF — EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision (ICLR 2024) · better on 3 of 3 shared results
- SUDS — SUDS: Scalable Urban Dynamic Scenes (CVPR 2023) · better on 3 of 3 shared results
- OmniRe — OmniRe: Omni Urban Scene Reconstruction (ICLR 2025) · better on 1 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
- FreeTimeGS: Free Gaussian Primitives at Anytime Anywhere for Dynamic Scene Reconstruction (CVPR 2025 · similarity 0.86)
- Fully Explicit Dynamic Gaussian Splatting (NeurIPS 2024 · similarity 0.86)
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (ICLR 2024 · similarity 0.86)
- HybridGS: Decoupling Transients and Statics with 2D and 3D Gaussian Splatting (CVPR 2025 · similarity 0.86)
- Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling (AAAI 2025 · similarity 0.86)
- Motion Decoupled 3D Gaussian Splatting for Dynamic Object Representation (AAAI 2025 · similarity 0.86)
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.
