RealVDeblur：用于通用真实世界视频去模糊的一步扩散法
RealVDeblur: One-Step Diffusion for Generalizable Real-World Video Deblurring
浏览论文内容
中文总结 AI 辅助
针对真实世界视频去模糊难题，提出RealVDeblur框架。构建模糊合成管道提供数据，利用视频扩散先验恢复，采用逐帧编码并简化采样为一步生成器，还有时间窗口掩码稳定推理，在多方面表现出色且提升3D重建鲁棒性。
中文摘要 AI 辅助
由于运动模式多样、退化复杂以及真实训练数据稀缺，真实世界视频去模糊仍具有挑战性，而稳健恢复对移动成像和3D重建等下游管道至关重要。本文提出RealVDeblur，一个旨在在各种真实捕获条件下提高野外鲁棒性的有效生成框架。首先构建大规模、基于物理的模糊合成管道以提供训练数据；其次利用视频扩散先验进行恢复，采用逐帧编码方案。通过多步扩散采样简化为一步生成器，以及无训练的时间窗口掩码来稳定推理。实验表明该方法在感知质量、语义保真度和时间一致性方面表现出色，在严重运动模糊下的下游3D重建中也具有更好的鲁棒性。
英文摘要
Real-world video deblurring remains challenging due to diverse motion patterns, complex degradations, and the scarcity of realistic training data, yet robust restoration is critical for downstream pipelines such as mobile imaging and 3D reconstruction. This work presents \textbf{RealVDeblur}, an efficient generative framework designed to improve in-the-wild robustness under diverse real capture conditions. First, a large-scale, physically grounded blur synthesis pipeline is constructed from scene-level 3D Gaussian Splatting (3DGS) assets and high-frame-rate videos, providing realistic training data covering both camera-induced and object-motion blur. Second, a video diffusion prior is leveraged for restoration; to better accommodate frame-dependent blur variations, temporal compression in the VAE is disabled and a frame-wise encoding scheme is adopted. For practical deployment on long videos, multi-step diffusion sampling is distilled into an efficient one-step generator, and a training-free Temporal Window Mask stabilizes inference beyond the training horizon with constant memory usage. Extensive experiments on diverse real-world benchmarks demonstrate strong perceptual quality, semantic fidelity, and temporal consistency on unseen videos, as well as improved robustness in downstream 3D reconstruction under severe motion blur. Project page: https://rbjin.github.io/RealVDeblur
发表机构
- Shanghai Jiao Tong University（上海交通大学）
- Shanghai AI Laboratory（上海人工智能实验室）
- CUHK MMLab（香港中文大学多媒体实验室）
- CPII under InnoHK（创新香港研究院下的CPII）
- Tsinghua University（清华大学）
机构由 AI 辅助整理，请以论文原文为准。
