利用视频编码信息提升去模糊效果，实现更清晰的动态画面恢复。
Coding-Prior Guided Diffusion Network for Video Deblurring
- 结合编码器提供的运动矢量与残差图，精准对齐帧间内容
- 在预训练扩散模型中引入编码先验，显著提升细节真实感
- 在多个数据集上指标领先，适合视频处理与重建任务
尽管近期视频去模糊方法已取得显著进展，但常忽略两类重要先验：（1）视频编码器提供的运动矢量（MVs）与编码残差（CRs），可提供高效的帧间对齐线索；（2）预训练扩散生成模型中蕴含的丰富真实世界知识。本文提出CPGDNet，一种两阶段新框架，有效融合编码先验与生成扩散先验以实现高质量去模糊。首先，编码先验特征传播（CPFP）模块利用运动矢量实现高效帧对齐，并通过编码残差生成注意力掩码，缓解运动不准确与纹理变化问题；其次，编码先验控制生成（CPC）模块将编码先验融入预训练扩散模型，引导其增强关键区域并合成逼真细节。实验表明，本方法在感知质量上达到当前最优，图像质量评估指标最高提升30%。代码与增强编码先验的数据集将开源。
原文摘要 · Abstract (English)
While recent video deblurring methods have advanced significantly, they often overlook two valuable prior information: (1) motion vectors (MVs) and coding residuals (CRs) from video codecs, which provide efficient inter-frame alignment cues, and (2) the rich real-world knowledge embedded in pre-trained diffusion generative models. We present CPGDNet, a novel two-stage framework that effectively leverages both coding priors and generative diffusion priors for high-quality deblurring. First, our coding-prior feature propagation (CPFP) module utilizes MVs for efficient frame alignment and CRs to generate attention masks, addressing motion inaccuracies and texture variations. Second, a coding-prior controlled generation (CPC) module network integrates coding priors into a pretrained diffusion model, guiding it to enhance critical regions and synthesize realistic details. Experiments demonstrate our method achieves state-of-the-art perceptual quality with up to 30% improvement in IQA metrics. Both the code and the codingprior-augmented dataset will be open-sourced.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。