Research map / 3D vision / Gaussian splatting
E2EGS: Event-to-Edge Gaussian Splatting for Pose-Free 3D Reconstruction
Yunsoo Kim, Changki Sung, Dasol Hong, Hyun Myung
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 edge-guided loss to random-init baseline (ablation) | IncEventGS† · Ablation sequence | ATE RMSE (cm): 6.62 -> 0.50 | Improved |
| add edge-guided Gaussian initialization to random-init baseline (ablation) | IncEventGS† · Ablation sequence | ATE RMSE (cm): 6.62 -> 0.29 | Improved |
| add edge loss on top of edge init (ablation) | E2EGS · Ablation sequence | ATE RMSE (cm): 0.29 -> 0.28 | Improved |
| replace depth-model init with edge init plus edge loss (ablation) | IncEventGS · Ablation sequence | ATE RMSE (cm): 0.37 -> 0.28 | Improved |
| increase edge ratio from 0.3 to 1.0 (ablation) | E2EGS · edge ratio sweep | ATE RMSE (cm): 0.40 -> 11.93 | Hurt |
| use no edge Gaussians (r_edge 0.0) instead of 0.1-0.3 (ablation) | E2EGS · edge ratio sweep | ATE RMSE (cm): 0.41 (0.1) vs 5.68 (0.0) | Hurt |
| E2EGS versus depth-initialized IncEventGS on real TUM-VIE | E2EGS · TUM-VIE | ATE RMSE (cm): 2.19 -> 1.12 (1d), 1.62 -> 0.65 (3d) | Improved |
| E2EGS versus depth-initialized IncEventGS on synthetic Replica | E2EGS · Replica | ATE RMSE (cm): room0 0.051 -> 0.049; office2 0.041 -> 0.070 | Mixed |
| E2EGS versus depth-initialized IncEventGS on NVS | E2EGS · Replica | PSNR: room2 23.25 -> 23.01; office2 21.27 -> 24.86 | Mixed |
Closest papers by meaning
- Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.92)
- EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.92)
- EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Rendering (CVPR 2025 · similarity 0.91)
- EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting (ICML 2024 · similarity 0.91)
- GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation (NeurIPS 2025 · similarity 0.90)
- AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scenes (AAAI 2025 · similarity 0.89)
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.
