Research map / Video / Video segmentation and tracking
Non-Uniform Exposure Imaging via Neuromorphic Shutter Control
Mingyuan Lin, Jian Liu, Chi Zhang, Zibo Zhao, Chu He, Lei Yu
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 masked event loss L_em-n2n to L_tc-n2n (ablation) | SEID · Vimeo-Triplet | PSNR: 34.150 -> 39.260 | Improved |
| use event mask M() in L_em-n2n (with L_tc-n2n) (ablation) | SEID · Vimeo-Triplet | PSNR: 34.150 -> 39.260 | Improved |
| add L_tc-n2n to masked L_em-n2n (ablation) | SEID · Vimeo-Triplet | PSNR: 35.417 -> 39.260 | Improved |
| add masked L_em-n2n to L_tc-n2n alone (EIP outputs) (ablation) | SEID · Vimeo-Triplet | SSIM: 0.976 -> 0.983 | Improved |
| replace uniform-exposure denoiser PCST with SEID | NSC_g · Vimeo-Triplet | PSNR: 38.737 -> 39.247 | Improved |
| use NSC shutter control with PCST instead of uniform exposure | PCST · Vimeo-Triplet | PSNR: 37.322 -> 38.737 | Improved |
| use pixel-wise (local motion) NSC_p instead of global NSC_g (ablation) | NSC+SEID · Vimeo-Triplet | PSNR: 39.247 -> 39.260 | No clear effect |
| use NSC_g instead of auto exposure | camera · KLT feature tracking | mean tracked points: 192 -> 283 | Improved |
| add SEID denoising to NSC_g | NSC_g · KLT feature tracking | min tracked points: 99 -> 151 | Improved |
| set threshold R to 20,000 (ablation) | NSC+SEID · Vimeo-Triplet | PSNR | Improved |
Closest papers by meaning
- EvUnroll: Neuromorphic Events Based Rolling Shutter Image Correction (CVPR 2022 · similarity 0.89)
- NeuroZoom: Denoising and Super Resolving Neuromorphic Events and Spikes (TPAMI 2023 · similarity 0.88)
- Joint Filtering of Intensity Images and Neuromorphic Events for High-Resolution Noise-Robust Imaging (CVPR 2020 · similarity 0.87)
- AE-NeRF: Augmenting Event-Based Neural Radiance Fields for Non-ideal Conditions and Larger Scenes (AAAI 2025 · similarity 0.84)
- LED: A Large-scale Real-world Paired Dataset for Event Camera Denoising (CVPR 2024 · similarity 0.84)
- USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields (ICLR 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.
