# D$^2$-VR: Degradation-Robust and Distilled Video Restoration with Synergistic Optimization Strategy

Source: [D$^2$-VR: Degradation-Robust and Distilled Video Restoration with Synergistic Optimization Strategy](<https://www.sota2.com/research/paper/698abbddc97a0b3e3b5de271>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-11T05:00:13.386Z

Authors: Jianfeng Liang, Shaocheng Shen, Botao Xu, Qiang Hu, Xiaoyun Zhang

Published: 2026-02-09T08:52:51.000Z

## Abstract

The integration of diffusion priors with temporal alignment has emerged as a transformative paradigm for video restoration, delivering fantastic perceptual quality, yet the practical deployment of such frameworks is severely constrained by prohibitive inference latency and temporal instability when confronted with complex real-world degradations. To address these limitations, we propose \\textbf{D$^2$-VR}, a single-image diffusion-based video-restoration framework with low-step inference. To obtain precise temporal guidance under severe degradation, we first design a Degradation-Robust Flow Alignment (DRFA) module that leverages confidence-aware attention to filter unreliable motion cues. We then incorporate an adversarial distillation paradigm to compress the diffusion sampling trajectory into a rapid few-step regime. Finally, a synergistic optimization strategy is devised to harmonize perceptual quality with rigorous temporal consistency. Extensive experiments demonstrate that D$^2$-VR achieves state-of-the-art performance while accelerating the sampling process by \\textbf{12$\\times$}

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Video Restoration on VideoLQ](<https://www.sota2.com/research/sota/video-restoration-on-videolq.md>): Video Restoration; VideoLQ; MUSIQ: 58.48.

- [Video Restoration on REDS30](<https://www.sota2.com/research/sota/video-restoration-on-reds30.md>): Video Restoration; REDS30; PSNR: 24.72.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.08395>)

[PDF](<https://arxiv.org/pdf/2602.08395.pdf>)