Research map / 3D vision / Gaussian splatting
STD-GS: Exploring Frame-Event Interaction for SpatioTemporal-Disentangled Gaussian Splatting to Reconstruct High-Dynamic Scene
Hanyu Zhou, Haonan Wang, Haoyue Liu, Yuxing Duan, Luxin Yan, Gim Hee Lee
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-level disentanglement (ablation) | STD-GS · CoFED high-dynamic | PSNR: 24.83 -> 26.15 | Improved |
| add object-level disentanglement (ablation) | STD-GS · CoFED high-dynamic | PSNR: 26.15 -> 26.89 | Improved |
| add Gaussian fusion (ablation) | STD-GS · CoFED high-dynamic | PSNR: 26.89 -> 27.26 | Improved |
| add color fusion (ablation) | STD-GS · CoFED high-dynamic | PSNR: 27.26 -> 27.68 | Improved |
| add appearance-motion clustering loss L_clu (ablation) | STD-GS · CoFED high-dynamic | PSNR: 25.78 -> 26.95 | Improved |
| add consistency loss L_consis (ablation) | STD-GS · CoFED high-dynamic | PSNR: 26.95 -> 27.68 | Improved |
| add L_consis to L_recon alone (ablation) | STD-GS · CoFED high-dynamic | PSNR: 25.78 -> 26.03 | Improved |
| train with frame-event data instead of events only (ablation) | STD-GS · CoFED high-dynamic | PSNR: 24.15 -> 27.68 | Improved |
| train with frame-event data instead of frames only (ablation) | STD-GS · CoFED high-dynamic | PSNR: 25.91 -> 27.68 | Improved |
| add frame interpolation (TimeLens) (ablation) | STD-GS · CoFED high-dynamic | PSNR: 26.25 -> 26.48 | Improved |
| add temporal tracking (ablation) | STD-GS · CoFED high-dynamic | PSNR: 26.25 -> 27.68 | Improved |
| use temporal tracking instead of frame interpolation (ablation) | STD-GS · CoFED high-dynamic | LPIPS: 0.31 -> 0.26 | Improved |
Closest papers by meaning
- Motion Decoupled 3D Gaussian Splatting for Dynamic Object Representation (AAAI 2025 · similarity 0.90)
- Superpoint Gaussian Splatting for Real-Time High-Fidelity Dynamic Scene Reconstruction (ICML 2024 · similarity 0.88)
- BARD-GS: Blur-Aware Reconstruction of Dynamic Scenes via Gaussian Splatting (CVPR 2025 · similarity 0.88)
- Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis (CVPR 2024 · similarity 0.88)
- MoDec-GS: Global-to-Local Motion Decomposition and Temporal Interval Adjustment for Compact Dynamic 3D Gaussian Splatting (CVPR 2025 · similarity 0.88)
- Bridge Frame and Event: Common Spatiotemporal Fusion for High-Dynamic Scene Optical Flow (CVPR 2025 · 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.
