Research map / Image generation / Image restoration
EventZoom: Learning To Denoise and Super Resolve Neuromorphic Events
Peiqi Duan, Zihao W. Wang, Xinyu Zhou, Yi Ma, Boxin Shi
Check 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 |
|---|---|---|---|
| Use EventZoom instead of Liu et al. | event denoising on DVSNOISE20 · DVSNOISE20 | runtime: 435.64 -> 10.65 | Improved |
| Use EventZoom instead of EV-gait | event denoising on DVSNOISE20 · DVSNOISE20 | runtime: 1706.41 -> 10.65 | Improved |
| Use EventZoom instead of GEF | event denoising on DVSNOISE20 · DVSNOISE20 | runtime: 5094.40 -> 10.65 | Improved |
| Use EventZoom instead of EDnCNN | event denoising on DVSNOISE20 · DVSNOISE20 | runtime: 626.83 -> 10.65 | Improved |
| Use EventZoom instead of E2SRI | event-based image reconstruction · EventNFS | PSNR: 14.787 -> 15.510 | Improved |
| Use EventZoom instead of E2SRI | event-based image reconstruction · EventNFS | SSIM: 0.474 -> 0.505 | Improved |
| Use EventZoom instead of E2SRI | event-based image reconstruction · EventNFS | MSE: 0.041 -> 0.036 | Improved |
| Use EventZoom instead of E2SRI | event-based image reconstruction · EventNFS | runtime: 6.297s -> 0.605s | Improved |
| Add E2I LR and HR image features (ablation) | EventZoom · EventNFS validation | MSE: 0.0608 -> 0.0568 | Improved |
| Add the E2I HR feature alongside the LR feature (ablation) | EventZoom · EventNFS validation | MSE: 0.0575 -> 0.0568 | Improved |
| Add the E2I LR feature alongside the HR feature (ablation) | EventZoom · EventNFS validation | MSE: 0.0580 -> 0.0568 | Improved |
Later papers that compared with this method
1 later accepted paper reports EventZoom as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- EDformer: Transformer-Based Event Denoising Across Varied Noise Levels (ECCV 2024 · better on 1 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
- NeuroZoom: Denoising and Super Resolving Neuromorphic Events and Spikes (TPAMI 2023 · similarity 0.91)
- EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision (AAAI 2025 · similarity 0.90)
- LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising (CVPR 2024 · similarity 0.88)
- AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scenes (AAAI 2025 · similarity 0.87)
- A Chaotic Dynamics Framework Inspired by Dorsal Stream for Event Signal Processing (ICML 2025 · similarity 0.86)
- Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · similarity 0.86)
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.
