Research map / Video / Video segmentation and tracking
Supervised Raw Video Denoising With a Benchmark Dataset on Dynamic Scenes
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Train RViDeNet with captured noisy-clean videos in addition to synthetic data | RViDeNet · Captured indoor videos (25 videos) | sRGB PSNR: 39.19 -> 39.95 | Helped |
| Process noisy videos in raw rather than sRGB (ablation) | RViDeNet · Captured indoor test set (ISO 1600–25600) | sRGB PSNR: 38.58 -> 39.69 | Helped |
| Add RGBG packing (ablation) | RViDeNet raw processing · Captured indoor test set (ISO 1600–25600) | sRGB PSNR: 39.69 -> 39.69 | No clear effect |
| Add RGBG packing (ablation) | RViDeNet raw processing · Captured indoor test set (ISO 1600–25600) | sRGB SSIM: 0.9776 -> 0.9778 | Helped |
| Add pre-denoising-guided alignment (ablation) | RViDeNet · Captured indoor test set (ISO 1600–25600) | sRGB PSNR: 39.69 -> 39.80 | Helped |
| Add pre-denoising-guided alignment (ablation) | RViDeNet · Captured indoor test set (ISO 1600–25600) | Raw PSNR: 43.84 -> 43.88 | Helped |
| Add non-local attention (ablation) | RViDeNet · Captured indoor test set (ISO 1600–25600) | sRGB PSNR: 39.80 -> 39.95 | Helped |
| Add non-local attention (ablation) | RViDeNet · Captured indoor test set (ISO 1600–25600) | Raw PSNR: 43.88 -> 43.97 | Helped |
| Use raw video processing rather than sRGB-domain processing (ablation) | RViDeNet · Captured indoor test set (ISO 1600–25600) | sRGB SSIM: 0.9703 -> 0.9776 | Helped |
| Use RViDeNet rather than EDVR | Captured indoor videos (25 videos) · Captured indoor videos (25 videos) | sRGB PSNR: 38.97 -> 39.95 | Helped |
Closest papers by meaning
- Classic Video Denoising in a Machine Learning World: Robust, Fast, and Controllable (CVPR 2025 · similarity 0.88)
- Real-Time Controllable Denoising for Image and Video (CVPR 2023 · similarity 0.88)
- IDR: Self-Supervised Image Denoising via Iterative Data Refinement (CVPR 2022 · similarity 0.87)
- TD²-Net: Toward Denoising and Debiasing for Video Scene Graph Generation (AAAI 2024 · similarity 0.87)
- APR-RD: Complemental Two Steps for Self-Supervised Real Image Denoising (AAAI 2025 · similarity 0.86)
- DFDNet: Disentangling and Filtering Dynamics for Enhanced Video Prediction (AAAI 2025 · 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.