Research map / Video / Video segmentation and tracking
HFR and HDR Video from Multi-Attenuated Spikes Using a Rapidly Rotating SpokeND Filter
Yakun Chang, Zhaojun Huang, Siqi Yang, Yeliduosi Xiaokaiti, Shikui Wei, Yao Zhao, Tiejun Huang, 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 ReGain module (recover relative gain from multi-attenuated spikes) (ablation) | ReST-Net · Synthetic test set | PSNR: 21.89 -> 34.27 | Improved |
| add ReGain module (ablation) | ReST-Net · Synthetic test set | SSIM: 0.789 -> 0.916 | Improved |
| add ReGain module (ablation) | ReST-Net · Synthetic test set | HDR-VQM: 0.724 -> 0.152 | Improved |
| add ReFine module (temporal refinement) (ablation) | ReST-Net · Synthetic test set | PSNR: 31.48 -> 34.27 | Improved |
| add ReFine module (ablation) | ReST-Net · Synthetic test set | SSIM: 0.900 -> 0.916 | Improved |
| add ReFine module (ablation) | ReST-Net · Synthetic test set | HDR-VDP3: 7.173 -> 7.501 | Improved |
| ReST-Net on multi-attenuated spikes versus TFI baseline reconstruction | spike reconstruction · Synthetic test set | PSNR: 21.75 -> 34.27 | Improved |
| ReST-Net versus the longest temporal window baseline (TFW-200) | spike reconstruction · Synthetic test set | PSNR: 29.05 -> 34.27 | Improved |
| increase test motion speed to 2x | ReST-Net · Synthetic test set | PSNR: 34.27 -> 29.91 | Hurt |
| increase test motion speed to 3x | ReST-Net · Synthetic test set | PSNR: 34.27 -> 26.35 | Hurt |
| apply synthetic-trained model to real-world data with defocused filter without retraining | ReST-Net · Real-world spike data | qualitative HDR reconstruction | No clear effect |
Closest papers by meaning
- Pix2HDR - A Pixel-Wise Acquisition and Deep Learning-Based Synthesis Approach for High-Speed HDR Videos (TPAMI 2024 · similarity 0.89)
- Towards HDR and HFR Video from Rolling-Mixed-Bit Spikings (CVPR 2024 · similarity 0.88)
- Single Shot HDR Recovery via a Video Diffusion Prior (NeurIPS 2026 · similarity 0.88)
- HDRFlow: Real-Time HDR Video Reconstruction with Large Motions (CVPR 2024 · similarity 0.87)
- EvHDR-GS: Event-guided HDR Video Reconstruction with 3D Gaussian Splatting (AAAI 2025 · similarity 0.87)
- Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Network (CVPR 2024 · 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.
