Research map / 3D vision / Gaussian splatting
EvaGaussians: Event Stream Assisted Gaussian Splatting from Blurry Images
Wangbo Yu, Chaoran Feng, Jianing Li, Jiye Tang, Jiashu Yang, Zhenyu Tang, Meng Cao, Xu Jia, Yuchao Yang, Li Yuan, Yonghong Tian
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 event reconstruction loss L_event to blur loss (ablation) | EvaGaussians · Large-scale | PSNR: 24.98 -> 25.71 | Improved |
| add event reconstruction loss L_event to blur loss (ablation) | EvaGaussians · Medium-scale | PSNR: 29.10 -> 29.94 | Improved |
| add event-assisted depth regularization L_depth (ablation) | EvaGaussians · Large-scale | PSNR: 25.71 -> 25.54 | Hurt |
| add event-assisted depth regularization L_depth (ablation) | EvaGaussians · Medium-scale | SSIM: .9098 -> .9139 | Improved |
| add intensity reconstruction loss L_int (ablation) | EvaGaussians · Large-scale | PSNR: 25.54 -> 26.02 | Improved |
| add intensity reconstruction loss L_int (ablation) | EvaGaussians · Real scene | BRISQUE: 56.17 -> 53.95 | Improved |
| add all event losses (L_event, L_depth, L_int) to blur loss only (ablation) | EvaGaussians · Medium-scale | PSNR: 29.10 -> 30.47 | Improved |
| optimize camera poses jointly instead of keeping initial COLMAP poses (ablation) | EvaGaussians · Large-scale | ATE: 0.3825 -> 0.0489 | Improved |
| optimize camera poses jointly (ablation) | EvaGaussians · Medium-scale | ATE: 0.0598 -> 0.0461 | Improved |
| increase number of optimized poses beyond 9 (ablation) | EvaGaussians · Large-scale | novel view quality | No clear effect |
| increase motion blur from mild to strong | EvaGaussians · City blocks | PSNR: 26.38 -> 25.04 | Mixed |
| use EvaGaussians instead of EDNeRF | event-assisted deblurring · Large-scale | PSNR: 24.63 -> 26.02 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- BAD-NeRF — BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields (CVPR 2023) · better on 3 of 3 shared results
- E2NeRF — E2NeRF: Event Enhanced Neural Radiance Fields from Blurry Images (ICCV 2023) · better on 3 of 3 shared results
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
- GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation (NeurIPS 2025 · similarity 0.92)
- EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting (ICML 2024 · similarity 0.92)
- DiET-GS: Diffusion Prior and Event Stream-Assisted Motion Deblurring 3D Gaussian Splatting (CVPR 2025 · similarity 0.92)
- EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.90)
- Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.90)
- Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting (CVPR 2025 · similarity 0.90)
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.
