Research map / Video / Video segmentation and tracking
Fast Window-Based Event Denoising With Spatiotemporal Correlation Enhancement
Huachen Fang, Jinjian Wu, Qibin Hou, Weisheng Dong, Guangming Shi
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 BEC unit (bone events check) instead of farthest sampling (ablation) | WedNet · DVSCLEAN | SNR: 21.65 -> 25.73 | Improved |
| add BEC unit instead of farthest sampling (ablation) | WedNet · DVSNOISE20 | RPMD: 35.49 -> 28.12 | Improved |
| add BEC unit instead of farthest sampling (ablation) | WedNet · ED-KoGTL | SNR: 22.31 -> 26.97 | Improved |
| increase iterative number in SSFE module (ablation) | WedNet · DVSCLEAN, DVSNOISE20, ED-KoGTL | SNR / RPMD | No clear effect |
| increase sampling event number in first sampling operation beyond sufficient level (ablation) | WedNet · DVSCLEAN, DVSNOISE20, ED-KoGTL | SNR / RPMD | Mixed |
| use SSFE module instead of Spatial Feature Embedding or Res-block (ablation) | WedNet · DVSCLEAN, DVSNOISE20, ED-KoGTL | SNR / RPMD | Improved |
| use WedNet instead of AEDNet | AEDNet · Denoising runtime on DVSNOISE20 | time (s): 8379.58 -> 427.54 | Improved |
| use WedNet instead of AEDNet on 100% noise ratio | AEDNet · DVSCLEAN (100% noise) | SNR: 25.08 -> 24.65 | Hurt |
| use WedNet instead of AEDNet | AEDNet · ED-KoGTL (average) | SNR: 25.54 -> 26.97 | Improved |
| denoise events with WedNet before HATS classification | HATS · MNIST-DVS | accuracy: 98.4% -> 99.1% | Improved |
| denoise events with WedNet before HATS classification | HATS · N-CARS | accuracy: 90.2% -> 92.1% | Improved |
| denoise events with WedNet before HATS classification | HATS · CIFAR10-DVS | accuracy: 52.4% -> 60.1% | Improved |
Closest papers by meaning
- Temporal As a Plugin: Unsupervised Video Denoising with Pre-Trained Image Denoisers (ECCV 2024 · similarity 0.87)
- EventZoom: Learning To Denoise and Super Resolve Neuromorphic Events (CVPR 2021 · similarity 0.87)
- LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising (CVPR 2024 · similarity 0.86)
- Learning Continuous Spatiotemporal Implicit Neural Fields for Unsupervised Video Denoising (TPAMI 2026 · similarity 0.86)
- Learning Scale-Aware Spatio-temporal Implicit Representation for Event-based Motion Deblurring (ICML 2024 · similarity 0.85)
- Motion Deblurring via Spatial-Temporal Collaboration of Frames and Events (AAAI 2024 · similarity 0.84)
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.
