Research map / Video / Video segmentation and tracking
Joint Filtering of Intensity Images and Neuromorphic Events for High-Resolution Noise-Robust Imaging
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 GEF to filter events before DMR frame reconstruction | DMR · Slider depth | PSNR: 25.10 -> 26.63 | Helped |
| Use GEF to filter events before DMR frame reconstruction | DMR · Slider depth | SSIM: 0.8237 -> 0.8614 | Helped |
| Jointly filter event and image information with GEF instead of no-guidance super-resolution | Event super-resolution · Simulated event super-resolution, 2× | PSNR: 40.837 -> 42.755 | Helped |
| Jointly filter event and image information with GEF instead of no-guidance super-resolution | Event super-resolution · Simulated event super-resolution, 4× | PSNR: 40.577 -> 43.319 | Helped |
| Jointly filter event and image information with GEF instead of no-guidance super-resolution | Event super-resolution · Simulated event super-resolution, 8× | PSNR: 40.152 -> 44.218 | Helped |
| Use joint filtering with an SR image rather than no-guidance super-resolution | Event super-resolution · Simulated event super-resolution | PSNR: 40.837 -> 42.603; 40.577 -> 43.037; 40.152 -> 44.170 | Helped |
| Replace the GEF mutual-structure filter with GIF (ablation) | GEF · Simulated event denoising | RMSE | Hurt |
| Replace the GEF mutual-structure filter with SW-GF (ablation) | GEF · Simulated event denoising | RMSE | Hurt |
| Use MS-JF rather than GIF or SW-GF as the joint filtering step (ablation) | GEF · Simulated event denoising | RMSE | Helped |
| Use an intensity image as guidance for event super-resolution | Event super-resolution · Simulated event super-resolution | PSNR: 40.110 -> 42.591; 39.133 -> 42.612; 39.368 -> 44.144 | Helped |
| Apply CNN super-resolution directly to event images rather than jointly filtering with image guidance | Event super-resolution · Simulated event super-resolution | PSNR: 40.837; 40.577; 40.152 vs 42.755; 43.319; 44.218 | Hurt |
| Estimate motion using image edges jointly with warped events rather than events alone (ablation) | Flow estimation · Simulated flow estimation under event noise | flow estimation error | Helped |
Closest papers by meaning
- Learning to Super Resolve Intensity Images From Events (CVPR 2020 · similarity 0.88)
- LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising (CVPR 2024 · similarity 0.86)
- Event-Enhanced Blurry Video Super-Resolution (AAAI 2025 · similarity 0.85)
- AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scenes (AAAI 2025 · similarity 0.85)
- Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach (CVPR 2024 · similarity 0.85)
- Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · similarity 0.85)
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.