Research map / Video / Video segmentation and tracking
High Frame Rate Video Reconstruction based on an Event Camera
Liyuan Pan, Richard Hartley, Cedric Scheerlinck, Miaomiao Liu, Xin Yu, Yuchao Dai
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 |
|---|---|---|---|
| use multiple-frame mEDI model instead of single-frame EDI | EDI · Synthetic dataset (deblurred images) | PSNR (dB): 29.06 -> 30.29 | Improved |
| use multiple-frame mEDI model instead of single-frame EDI | EDI · Synthetic dataset (deblurred images) | SSIM: 0.9430 -> 0.9194 | Hurt |
| use mEDI instead of EDI for video reconstruction | EDI · Synthetic dataset (reconstructed videos) | PSNR (dB): 28.49 -> 28.83 | Improved |
| use mEDI instead of EDI for video reconstruction | EDI · Synthetic dataset (reconstructed videos) | SSIM: 0.9199 -> 0.9098 | Hurt |
| jointly use events and blurred frame instead of deblur-then-reconstruct (Baseline 1) | mEDI · Synthetic dataset (reconstructed videos) | PSNR (dB): 25.52 -> 28.83 | Improved |
| jointly use events and blurred frame instead of reconstruct-then-deblur (Baseline 2) | mEDI · Synthetic dataset (reconstructed videos) | PSNR (dB): 26.34 -> 28.83 | Improved |
| use mEDI instead of learned deblurring Tao | mEDI · Synthetic dataset (deblurred images) | PSNR (dB): 30.26 -> 30.29 | Improved |
Closest papers by meaning
- Bringing a Blurry Frame Alive at High Frame-Rate With an Event Camera (CVPR 2019 · similarity 0.97)
- Learning to Super Resolve Intensity Images From Events (CVPR 2020 · similarity 0.90)
- EventAid: Benchmarking Event-Aided Image/Video Enhancement Algorithms With Real-Captured Hybrid Dataset (TPAMI 2025 · similarity 0.90)
- E2SRI: Learning to Super-Resolve Intensity Images From Events (TPAMI 2021 · similarity 0.90)
- High Speed and High Dynamic Range Video with an Event Camera (TPAMI 2019 · similarity 0.90)
- E2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning (AAAI 2024 · similarity 0.88)
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.
