Research map / 3D vision / Gaussian splatting
Event-boosted Deformable 3D Gaussians for Dynamic Scene Reconstruction
Wenhao Xu, Wenming Weng, Yueyi Zhang, Ruikang Xu, Zhiwei Xiong
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 GS-threshold joint modeling (GTJM) (ablation) | Event-boosted deformable 3D-GS · Synthetic ablation | PSNR: 29.39 -> 31.56 | Improved |
| add joint optimization of threshold and Gaussians within GTJM (ablation) | GTJM · Synthetic ablation | PSNR: 30.87 -> 31.56 | Improved |
| add dynamic-static decomposition (DSD) (ablation) | Event-boosted deformable 3D-GS · Synthetic ablation | PSNR: 30.78 -> 31.56 | Improved |
| add dynamic-static decomposition (DSD) (ablation) | Event-boosted deformable 3D-GS · Synthetic ablation | FPS: 57 -> 156 | Improved |
| add buffer-based soft decomposition (ablation) | DSD · Synthetic ablation | PSNR: 31.02 -> 31.56 | Improved |
| add buffer-based soft decomposition (ablation) | DSD · Synthetic ablation | FPS: 138 -> 156 | Improved |
| add RGB-assisted threshold estimation before 3D reconstruction (ablation) | 3D-GS with event supervision · Synthetic scenes | PSNR: 24.46 -> 26.63 | Improved |
| use frozen trained 3D-GS to refine threshold (ablation) | threshold modeling · Synthetic scenes | threshold MSE (x1e-4): 8.317 -> 7.077 | Improved |
| jointly fine-tune threshold and 3D-GS in stage two (ablation) | GTJM · Synthetic scenes | PSNR: 26.63 -> 28.01 | Improved |
| add events with threshold modeling over Event-4DGS | Event-4DGS · Synthetic dataset | PSNR: 2.73 dB average PSNR improvement | Improved |
| add event supervision to Deformable-3DGS (Event-4DGS) | Deformable-3DGS · Synthetic dataset | PSNR: 3.28 dB average PSNR improvement | Improved |
| use events and deblurring with our method on blurry scenes | Deformable-3DGS · Blurry dynamic scenes | PSNR: 4.79 dB in PSNR | Improved |
Closest papers by meaning
- Motion Decoupled 3D Gaussian Splatting for Dynamic Object Representation (AAAI 2025 · similarity 0.92)
- Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction (CVPR 2024 · similarity 0.91)
- MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.91)
- EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting (ICML 2024 · similarity 0.91)
- Fully Explicit Dynamic Gaussian Splatting (NeurIPS 2024 · similarity 0.91)
- EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Rendering (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.
