Research map / 3D vision / Gaussian splatting
TIDES: Time-Derivative Event Simulation via Deformable Reconstruction
Christopher Thirgood, Dipon Kumar Ghosh, Simon Hadfield
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 analytic time-tangent slope instead of finite differences (ablation) | TIDES · EDS | IG-NLL: 0.00521 -> 0.00373 | Improved |
| add analytic time-tangent slope instead of finite differences (ablation) | TIDES · EDS | Chamfer: 0.04801 -> 0.04262 | Improved |
| add multi-crossing per step (ablation) | TIDES · EDS | IG-NLL: 0.00439 -> 0.00373 | Improved |
| add adaptive step size controller (ablation) | TIDES · EDS | IG-NLL: 0.00486 -> 0.00373 | Improved |
| add risk-gated refinement (ablation) | TIDES · EDS | IG-NLL: 0.00458 -> 0.00373 | Improved |
| add mixed-visibility masking (ablation) | TIDES · EDS | IG-NLL: 0.00422 -> 0.00373 | Improved |
| add alpha-dot cue (ablation) | TIDES · EDS | IG-NLL: 0.00461 -> 0.00373 | Improved |
| add readout model (ablation) | TIDES · EDS | IG-NLL: 0.00388 -> 0.00373 | Improved |
| add adaptivity over compute-matched fixed queries (ablation) | TIDES · EDS | IG-NLL: 0.00405 -> 0.00373 | Improved |
| adaptive stepping over fixed 10x query schedule | TIDES · HS-ERGB | IG-NLL: 0.004984 -> 0.002343 | Improved |
| adaptive stepping over fixed 10x query schedule | TIDES · EDS | Fano error: 0.228440 -> 0.338062 | Hurt |
| combine baseline simulators with adaptive rendering | ESIM, V2E, DVS-Voltmeter, ICNS · EDS, DSEC, HS-ERGB, BS-ERGB | fidelity | Hurt |
Closest papers by meaning
- EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Rendering (CVPR 2025 · similarity 0.88)
- Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.88)
- GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation (NeurIPS 2025 · similarity 0.87)
- EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.87)
- EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting (ICML 2024 · similarity 0.86)
- E-Motion: Future Motion Simulation via Event Sequence Diffusion (NeurIPS 2024 · similarity 0.85)
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.
