Research map / Video / Video segmentation and tracking
Seeing Dynamic Scene in the Dark: A High-Quality Video Dataset With Mechatronic Alignment
Ruixing Wang, Xiaogang Xu, Chi-Wing Fu, Jiangbo Lu, Bei Yu, Jiaya Jia
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 progressive alignment (PAL) (ablation) | Ours w/o IMP, SNE · SDSD | PSNR: 22.61 -> 24.47 | Improved |
| add progressive alignment (PAL) (ablation) | Ours w/o IMP, SNE · SMID | PSNR: 25.04 -> 25.32 | Improved |
| add progressive alignment (PAL) (ablation) | Ours w/o IMP, SNE · SDSD | SSIM: 0.64 -> 0.65 | Improved |
| add illumination prediction (IMP) (ablation) | Ours with PAL, w/o SNE · SDSD | PSNR: 24.47 -> 24.53 | Improved |
| add illumination prediction (IMP) (ablation) | Ours with PAL, w/o SNE · SMID | PSNR: 25.32 -> 25.71 | Improved |
| add illumination prediction (IMP) (ablation) | Ours with PAL, w/o SNE · SMID | SSIM: 0.71 -> 0.74 | Improved |
| add self-supervised noise estimation (SNE) (ablation) | Ours with PAL and IMP · SDSD | PSNR: 24.53 -> 24.92 | Improved |
| add self-supervised noise estimation (SNE) (ablation) | Ours with PAL and IMP · SDSD | SSIM: 0.67 -> 0.73 | Improved |
| add self-supervised noise estimation (SNE) (ablation) | Ours with PAL and IMP · SMID | PSNR: 25.71 -> 26.03 | Improved |
| add self-supervised noise estimation (SNE) (ablation) | Ours with PAL and IMP · SMID | SSIM: 0.74 -> 0.75 | Improved |
| use the proposed method instead of the best baseline SMID [4] | low-light video enhancement · SMID | PSNR: 24.78 -> 26.03 | Improved |
| use the proposed method instead of the best baseline SMID [4] | low-light video enhancement · SDSD | PSNR: 24.09 -> 24.92 | Improved |
Closest papers by meaning
- Dancing in the Dark: A Benchmark towards General Low-light Video Enhancement (ICCV 2023 · similarity 0.89)
- Light-X: Generative 4D Video Rendering with Camera and Illumination Control (ICLR 2026 · similarity 0.88)
- Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approach (CVPR 2024 · similarity 0.88)
- EvLight++: Low-Light Video Enhancement With an Event Camera: A Large-Scale Real-World Dataset, Novel Method, and More (TPAMI 2025 · similarity 0.88)
- Seeing Motion at Nighttime with an Event Camera (CVPR 2024 · similarity 0.87)
- DynaTokens: Teaching Dynamics to Camera-Controlled Video Models at Test Time (NeurIPS 2026 · 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.
