Research map / Video / Video segmentation and tracking
NEST: Neural Event Stack for Event-Based Image Enhancement
Minggui Teng, Chu Zhou, Hanyue Lou, Boxin 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 global residual connection (ablation) | NEST D-Net · Deblurring | PSNR/SSIM/LPIPS: 30.74 -> 32.56 PSNR; 0.8932 -> 0.9354 SSIM; 0.0569 -> 0.0422 LPIPS | Improved |
| add global residual connection (ablation) | NEST S-Net · Super-resolution | PSNR/SSIM/LPIPS: 28.66 -> 29.43 PSNR; 0.7917 -> 0.8128 SSIM; 0.3075 -> 0.2745 LPIPS | Improved |
| add feature extractor in NEST estimator (ablation) | NEST D-Net · Deblurring | PSNR/SSIM/LPIPS: 31.68 -> 32.56 PSNR; 0.9064 -> 0.9354 SSIM; 0.0520 -> 0.0422 LPIPS | Improved |
| add feature extractor in NEST estimator (ablation) | NEST S-Net · Super-resolution | PSNR/SSIM/LPIPS: 29.20 -> 29.43 PSNR; 0.8096 -> 0.8128 SSIM; 0.2768 -> 0.2745 LPIPS | Improved |
| replace event stack with NEST representation in eSL-Net | eSL-Net · Deblurring | PSNR/SSIM/LPIPS: 29.73 -> 29.92 PSNR; 0.8697 -> 0.8935 SSIM; 0.1078 -> 0.0634 LPIPS | Improved |
| replace event stack with NEST representation in eSL-Net | eSL-Net · Super-resolution | PSNR/SSIM/LPIPS: 28.23 -> 28.87 PSNR; 0.7783 -> 0.7961 SSIM; 0.3950 -> 0.3096 LPIPS | Improved |
| use NEST instead of event stack (EvST) with the same D-Net/S-Net | D-Net/S-Net · Deblurring | PSNR/LPIPS: 31.09 -> 32.56 PSNR; 0.0689 -> 0.0422 LPIPS | Improved |
| use NEST instead of event stack (EvST) with the same D-Net/S-Net | D-Net/S-Net · Super-resolution | PSNR/LPIPS: 28.89 -> 29.43 PSNR; 0.3150 -> 0.2745 LPIPS | Improved |
| use NEST instead of MatrixLSTM representation | D-Net/S-Net · Deblurring | PSNR/LPIPS: 31.28 -> 32.56 PSNR; 0.0596 -> 0.0422 LPIPS | Improved |
| use NEST instead of EST representation | D-Net/S-Net · Super-resolution | PSNR: 13.14 -> 29.43 | Improved |
Closest papers by meaning
- End-to-End Learning of Representations for Asynchronous Event-Based Data (ICCV 2019 · similarity 0.88)
- EventNet: Asynchronous Recursive Event Processing (CVPR 2019 · similarity 0.88)
- EventZoom: Learning To Denoise and Super Resolve Neuromorphic Events (CVPR 2021 · similarity 0.88)
- EventZoom: A Progressive Approach to Event-Based Data Augmentation for Enhanced Neuromorphic Vision (AAAI 2025 · similarity 0.87)
- Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · similarity 0.87)
- Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach (CVPR 2024 · 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.
