Research map / Video / Video segmentation and tracking
Deep Parametric 3D Filters for Joint Video Denoising and Illumination Enhancement in Video Super Resolution
Xiaogang Xu, Ruixing Wang, Chi-Wing Fu, 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 |
|---|---|---|---|
| Use DP3DF for joint super-resolution, denoising, and illumination enhancement | LLN-to-HNN video reconstruction · SMID | PSNR: 24.89 -> 25.73 | Improved |
| Use DP3DF for joint super-resolution, denoising, and illumination enhancement | LLN-to-HNN video reconstruction · SDSD Indoor | PSNR: 26.32 -> 27.11 | Improved |
| Use DP3DF for joint super-resolution, denoising, and illumination enhancement | LLN-to-HNN video reconstruction · SDSD Outdoor | PSNR: 23.83 -> 25.80 | Improved |
| Add temporal filtering to DP3DF (ablation) | DP3DF · SMID, SDSD Indoor, SDSD Outdoor | PSNR: 23.67 -> 25.73; 25.49 -> 27.11; 24.98 -> 25.80 | Improved |
| Add temporal filtering to DP3DF (ablation) | DP3DF · SMID, SDSD Indoor, SDSD Outdoor | SSIM: 0.69 -> 0.73; 0.83 -> 0.85; 0.75 -> 0.77 | Improved |
| Add spatial filtering to DP3DF (ablation) | DP3DF · SMID, SDSD Indoor, SDSD Outdoor | PSNR: 22.84 -> 25.73; 24.87 -> 27.11; 24.02 -> 25.80 | Improved |
| Add spatial filtering to DP3DF (ablation) | DP3DF · SMID, SDSD Indoor, SDSD Outdoor | SSIM: 0.63 -> 0.73; 0.78 -> 0.85; 0.71 -> 0.77 | Improved |
| Add the residual learning branch (ablation) | DP3DF video reconstruction · SMID, SDSD Indoor, SDSD Outdoor | PSNR: 25.44 -> 25.73; 27.01 -> 27.11; 25.69 -> 25.80 | Improved |
| Add the residual learning branch (ablation) | DP3DF video reconstruction · SMID, SDSD Indoor, SDSD Outdoor | SSIM: 0.71 -> 0.73; 0.83 -> 0.85; 0.76 -> 0.77 | Improved |
Closest papers by meaning
- CycleISP: Real Image Restoration via Improved Data Synthesis (CVPR 2020 · similarity 0.87)
- Fast Spatio-Temporal Residual Network for Video Super-Resolution (CVPR 2019 · similarity 0.87)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 2025 · similarity 0.86)
- Intrinsic Phase-Preserving Networks for Depth Super Resolution (AAAI 2024 · similarity 0.85)
- LiBrA-Net: Lie-Algebraic Bilateral Affine Fields for Real-Time 4K Video Dehazing (NeurIPS 2026 · similarity 0.85)
- Video Depth Anything: Consistent Depth Estimation for Super-Long Videos (CVPR 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.
