Research map / Video / Video segmentation and tracking
Robust e-NeRF: NeRF from Sparse & Noisy Events under Non-Uniform Motion
Weng Fei Low, 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 speed-normalized losses (Robust e-NeRF) instead of Ev-NeRF accumulation-based losses | event NeRF · Synthetic 360 scenes, speed v=1/8x | PSNR: 19.79 -> 28.19 | Improved |
| add pixel-wise (non-accumulated) losses robust to threshold variation | event NeRF · Threshold std 0.06 | PSNR: 8.07 -> 28.23 | Improved |
| add refractory period modeling (ablation) | Robust e-NeRF · Ablation, medium | PSNR: 12.77 -> 24.10 | Improved |
| add target-normalized gradient loss (ablation) | Robust e-NeRF · Ablation, medium | PSNR: 23.15 -> 24.10 | Improved |
| add target-normalized gradient loss (ablation) | Robust e-NeRF · Ablation, easy | PSNR: 27.96 -> 28.19 | Improved |
| jointly optimize contrast thresholds from poor initialization | Robust e-NeRF · Threshold std 0.03 | PSNR: 28.14 -> 27.91 | No clear effect |
| jointly optimize thresholds in Ev-NeRF | Ev-NeRF · Threshold std 0.00 | PSNR: 27.72 -> 27.43 | Hurt |
| jointly optimize refractory period from poor initialization | Robust e-NeRF · Refractory period 25 ms | PSNR: 25.51 -> 22.48 | Hurt |
| jointly optimize thresholds and tau under collective hard setting | Robust e-NeRF · Collective, hard | PSNR: 23.51 -> 18.83 | Hurt |
| jointly optimize thresholds in Ev-NeRF under refractory period | Ev-NeRF · Refractory period 8 ms | PSNR: 13.17 -> 13.56 | No clear effect |
Later papers that compared with this method
1 later accepted paper reports Robust e-NeRF as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Deblur e-NeRF: NeRF from Motion-Blurred Events under High-speed or Low-light Conditions (ECCV 2024 · better on 10 of 10 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
- AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scenes (AAAI 2025 · similarity 0.94)
- Mitigating Motion Blur in Neural Radiance Fields with Events and Frames (CVPR 2024 · similarity 0.90)
- EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Rendering (CVPR 2025 · similarity 0.89)
- Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.88)
- EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.87)
- LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising (CVPR 2024 · similarity 0.87)
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.
