Research map / Image generation / Super-resolution
DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolution
Zhengyao Lv, Menghan Xia, Xintao Wang, Kwan-Yee K. Wong
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 Dual-Stream Distillation after stage I (ablation) | DUO-VSR · AIGC60 | NIQE: 5.45 -> 4.64 | Improved |
| add Preference-Guided Refinement (ablation) | DUO-VSR · AIGC60 | NIQE: 4.64 -> 4.42 | Improved |
| add Progressive Guided Distillation initialization (ablation) | DUO-VSR · AIGC60 | NIQE: 5.11 -> 4.42 | Improved |
| use DMD and RFS-GAN jointly vs DMD only (ablation) | dual-stream distillation · AIGC60 | NIQE: 4.99 -> 4.42 | Improved |
| use DMD and RFS-GAN jointly vs RFS-GAN only (ablation) | dual-stream distillation · AIGC60 | CLIPIQA: 0.427 -> 0.489 | Improved |
| joint optimization instead of sequential DMD then GAN (ablation) | dual-stream distillation · AIGC60 | DOVER: 87.67 -> 88.15 | Improved |
| full pipeline vs base 50-step model on perceptual metrics (ablation) | DUO-VSR · AIGC60 | CLIPIQA: 0.4712 -> 0.489 | Improved |
| one-step DUO-VSR vs SeedVR2-7B on fidelity | DUO-VSR · SPMCS | PSNR: 23.08 -> 22.90 | Hurt |
| one-step distillation vs multi-step MGLD | DUO-VSR · inference time | time (s): 956.7 -> 11.3 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DOVE — DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution (NeurIPS 2025) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Improved Adversarial Diffusion Compression for Real-World Video Super-Resolution (ICLR 2026 · similarity 0.90)
- Adversarial Score Distillation for Stable One-Step Diffusion in Real-World Image Super-Resolution (ECCV 2026 · similarity 0.90)
- FRAMER: Frequency-Aligned Self-Distillation with Adaptive Modulation Leveraging Diffusion Priors for Real-World Image Super-Resolution (CVPR 2026 · similarity 0.89)
- Noise-Started One-Step Image Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement (NeurIPS 2026 · similarity 0.87)
- Adversarial Diffusion Compression for Real-World Image Super-Resolution (CVPR 2025 · similarity 0.87)
- VideoGigaGAN: Towards Detail-rich Video Super-Resolution (CVPR 2025 · similarity 0.87)
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.
