Research map / 3D vision / NeRF and radiance fields
E 3 NeRF: Efficient Event-Enhanced Neural Radiance Fields From Blurry Images
Yunshan Qi, Jia Li, Yifan Zhao, Yu Zhang, Lin Zhu
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-guided spatial-temporal blur model (E3NeRF vs E2NeRF) | E2NeRF · Synthetic blur view, severe shake | PSNR: 26.82 -> 29.12 | Improved |
| add event-guided spatial-temporal blur model (E3NeRF vs E2NeRF) | E2NeRF · Synthetic blur view, slight shake | PSNR: 30.65 -> 31.41 | No clear effect |
| add event-guided spatial-temporal blur model (E3NeRF vs E2NeRF) | E2NeRF · Real-World-Challenge | PSNR: 29.92 -> 31.40 | Improved |
| add event-guided spatial-temporal blur model (E3NeRF vs E2NeRF) | E2NeRF · Real-World-Blur | RankIQA: 3.609 -> 3.243 | Improved |
| use only 25 forward-facing views instead of 100 360-degree views | E3NeRF · Synthetic blur view, slight shake | PSNR: 31.41 -> 32.56 | Improved |
| train NeRF on events with EDI deblurring instead of EDI alone | EDI · Synthetic blur view, slight shake | PSNR: 28.74 -> 29.43 | Improved |
| add images as supervision to event-only NeRF | e-NeRF · TUM-VIE mocap-1d-trans | PSNR: 15.60 -> 30.18 | Improved |
| add ground-truth poses and extra events to Ev-DeblurNeRF | Ev-DeblurNeRF · Ev-DeblurCDAVIS (full views) | PSNR: 29.08 -> 32.96 | Improved |
| reduce input views to 1/3 | Ev-DeblurNeRF · Ev-DeblurCDAVIS | PSNR: 29.08 -> 24.97 | Hurt |
| reduce input views to 1/3 | E3NeRF · Ev-DeblurCDAVIS | PSNR: 31.34 -> 30.08 | Hurt |
Later papers that compared with this method
1 later accepted paper reports E3NeRF as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Seeing through Light and Darkness: Sensor-Physics Grounded Deblurring HDR NeRF from Single-Exposure Images and Events (CVPR 2026 · better on 1 of 1 shared result)
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.
- E2NeRF — E2NeRF: Event Enhanced Neural Radiance Fields from Blurry Images (ICCV 2023) · better on 9 of 9 shared results
- DP-NeRF — DP-NeRF: Deblurred Neural Radiance Field With Physical Scene Priors (CVPR 2023) · better on 1 of 1 shared result
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
- Mitigating Motion Blur in Neural Radiance Fields with Events and Frames (CVPR 2024 · similarity 0.94)
- AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scenes (AAAI 2025 · similarity 0.93)
- DynaMoDe-NeRF: Motion-aware Deblurring Neural Radiance Field for Dynamic Scenes (CVPR 2025 · similarity 0.90)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.89)
- NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 2024 · similarity 0.89)
- EventSplat: 3D Gaussian Splatting from Moving Event Cameras for Real-time Rendering (CVPR 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.
