Research map / Video / Video segmentation and tracking
Lightweight High-Speed Photography Built on Coded Exposure and Implicit Neural Representation of Videos
Zhihong Zhang, Runzhao Yang, Jinli Suo, Yuxiao Cheng, Qionghai 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 |
|---|---|---|---|
| add coded exposure (ablation) | BDINR · GoPro | PSNR (dB): 26.12 -> 30.64 | Improved |
| add coded exposure (ablation) | BDINR · WAIC TSR | PSNR (dB): 27.19 -> 29.32 | Improved |
| add self-recursive strategy (ablation) | BDINR · GoPro | PSNR (dB): 30.10 -> 30.64 | Improved |
| add self-recursive strategy (ablation) | BDINR · WAIC TSR | PSNR (dB): 28.00 -> 29.32 | Improved |
| add temporal embedding module (ablation) | BDINR · GoPro | PSNR (dB): 30.45 -> 30.64 | Improved |
| add temporal embedding module (ablation) | BDINR · WAIC TSR | PSNR (dB): 28.38 -> 29.32 | Improved |
| add SSIM loss to Charbonnier loss (ablation) | BDINR · GoPro | PSNR (dB): 28.89 -> 30.22 | Improved |
| add edge loss (ablation) | BDINR · GoPro | PSNR (dB): 30.22 -> 30.26 | No clear effect |
| add reblur loss (ablation) | BDINR · GoPro | PSNR (dB): 30.26 -> 30.64 | Improved |
| increase coded exposure sequence length from 4 to 12 bits (ablation) | BDINR · GoPro | PSNR (dB): 34.60 -> 25.21 | Hurt |
| lower duty ratio below 5/8 (ablation) | BDINR · GoPro | PSNR (dB): 30.64 -> 26.02 | Hurt |
| raise duty ratio above 5/8 (ablation) | BDINR · GoPro | PSNR (dB): 30.64 -> 30.24 | Hurt |
Closest papers by meaning
- Exposure Trajectory Recovery From Motion Blur (TPAMI 2021 · similarity 0.87)
- Motion Blur Decomposition with Cross-shutter Guidance (CVPR 2024 · similarity 0.87)
- Joint Video Multi-Frame Interpolation and Deblurring Under Unknown Exposure Time (CVPR 2023 · similarity 0.86)
- Bringing Alive Blurred Moments (CVPR 2019 · similarity 0.86)
- From Motion Blur to Motion Flow: A Deep Learning Solution for Removing Heterogeneous Motion Blur (CVPR 2017 · similarity 0.86)
- DynaMoDe-NeRF: Motion-aware Deblurring Neural Radiance Field for Dynamic Scenes (CVPR 2025 · 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.
