用物理仿真数据训练扩散模型，一步生成清晰视频。
RealVDeblur: One-Step Diffusion for Generalizable Real-World Video Deblurring
- 基于3DGS和高速视频合成逼真模糊数据，覆盖多种运动模糊场景。
- 通过帧级编码与单步采样，实现高效推理且保持时序一致性。
- 无需微调即可稳定处理长视频，适合移动端和三维重建应用。
真实世界视频去模糊因多样的运动模式、复杂的退化过程以及缺乏真实训练数据而极具挑战性，但鲁棒的恢复对移动成像和三维重建等下游任务至关重要。本文提出 extbf{RealVDeblur}，一种高效生成框架，旨在提升在复杂真实拍摄条件下的鲁棒性。首先，利用场景级3D高斯点云（3DGS）资产与高帧率视频构建大规模、物理可信的模糊合成管道，生成涵盖相机运动与物体运动模糊的真实训练数据。其次，采用视频扩散先验进行修复；为适应帧间模糊差异，禁用VAE中的时序压缩，并引入帧级编码机制。针对长视频实际部署需求，将多步扩散采样蒸馏为高效的一步生成器，并设计无训练的时序窗口掩码，在恒定内存下稳定推断超出训练时长的视频。在多个真实世界基准上的实验表明，该方法在未见视频上表现出优异的感知质量、语义保真度和时序一致性，且在严重运动模糊下显著提升下游三维重建的鲁棒性。
原文摘要 · Abstract (English)
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
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。