Research map / Video / Video segmentation and tracking
Rethinking Diffusion Model-Based Video Super-Resolution: Leveraging Dense Guidance from Aligned Features
Jingyi Xu, Meisong Zheng, Ying Chen, Minglang Qiao, Xin Deng, Mai Xu
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 dense guidance (full U-Net guiding module) (ablation) | DGAF-VSR · REDS (ablation, 4x) | PSNR: 27.81 -> 28.17 | Improved |
| add dense guidance (ablation) | DGAF-VSR · REDS (ablation, 4x) | tLPIPS: 6.25 -> 3.92 | Improved |
| add dense guidance (ablation) | DGAF-VSR · REDS (ablation, 4x) | LPIPS: 0.104 -> 0.095 | Improved |
| warp at upscaled resolution (bicubic) instead of original resolution (ablation) | DGAF-VSR · REDS (ablation, 4x) | PSNR: 26.70 -> 28.13 | Improved |
| warp at upscaled resolution (bicubic) instead of original resolution (ablation) | DGAF-VSR · REDS (ablation, 4x) | tLPIPS: 21.61 -> 4.28 | Improved |
| use nearest neighbor instead of bicubic rescaling in warping (ablation) | DGAF-VSR · REDS (ablation, 4x) | PSNR: 28.13 -> 28.17 | Improved |
| use nearest neighbor instead of bicubic rescaling in warping (ablation) | DGAF-VSR · REDS (ablation, 4x) | LPIPS: 0.099 -> 0.095 | Improved |
| use nearest neighbor instead of bicubic rescaling in warping (ablation) | DGAF-VSR · REDS (ablation, 4x) | tLPIPS: 4.28 -> 3.92 | Improved |
| DGAF-VSR vs StableVSR (full method) | DGAF-VSR · REDS4 (4x) | PSNR: 27.97 -> 28.17 | Improved |
| DGAF-VSR vs best non-DM method on fidelity | DGAF-VSR · REDS4 (4x) | PSNR: 32.75 -> 28.17 | Hurt |
Closest papers by meaning
- DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution (NeurIPS 2025 · similarity 0.91)
- PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution (CVPR 2025 · similarity 0.91)
- One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution (NeurIPS 2025 · similarity 0.90)
- SkipSR: Faster Super-Resolution with Token Skipping (NeurIPS 2026 · similarity 0.90)
- SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution (NeurIPS 2024 · similarity 0.90)
- Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution (CVPR 2024 · similarity 0.89)
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.
