让模糊单目视频生成清晰动态3D画面，端到端搞定运动模糊问题。
MoBGS: Motion Deblurring Dynamic 3D Gaussian Splatting for Blurry Monocular Video
- 用自适应神经微分方程建模相机轨迹，解决运动模糊导致的视角估计偏差。
- 在Stereo Blur数据集上优于最新方法，动态新视角合成质量显著提升。
- 适合做视频去模糊、3D重建的开发者，尤其关注真实拍摄模糊视频场景。
我们提出MoBGS，一种新型运动去模糊3D高斯点云框架，能够从模糊单目视频中端到端重建出清晰高质量的新时空视角。现有动态新视角合成方法对随意拍摄视频中的运动模糊极为敏感，导致渲染质量大幅下降。尽管近期方法已尝试处理模糊输入，但主要聚焦静态场景重建，缺乏对动态物体的专门运动建模。为克服这些局限，我们的MoBGS引入一种新的模糊自适应潜在相机估计（BLCE）方法，采用提出的模糊自适应神经常微分方程（ODE）求解器，有效实现潜在相机轨迹估计，改善全局相机运动去模糊。此外，我们提出潜在相机诱导的曝光估计（LCEE）方法，确保全局相机与局部物体运动的去模糊一致性。在Stereo Blur数据集和真实模糊视频上的大量实验表明，我们的MoBGS显著优于近期方法，在运动模糊下的动态新视角合成任务中达到最先进性能。
原文摘要 · Abstract (English)
We present MoBGS, a novel motion deblurring 3D Gaussian Splatting (3DGS) framework capable of reconstructing sharp and high-quality novel spatio-temporal views from blurry monocular videos in an end-to-end manner. Existing dynamic novel view synthesis (NVS) methods are highly sensitive to motion blur in casually captured videos, resulting in significant degradation of rendering quality. While recent approaches address motion-blurred inputs for NVS, they primarily focus on static scene reconstruction and lack dedicated motion modeling for dynamic objects. To overcome these limitations, our MoBGS introduces a novel Blur-adaptive Latent Camera Estimation (BLCE) method using a proposed Blur-adaptive Neural Ordinary Differential Equation (ODE) solver for effective latent camera trajectory estimation, improving global camera motion deblurring. In addition, we propose a Latent Camera-induced Exposure Estimation (LCEE) method to ensure consistent deblurring of both a global camera and local object motions. Extensive experiments on the Stereo Blur dataset and real-world blurry videos show that our MoBGS significantly outperforms the very recent methods, achieving state-of-the-art performance for dynamic NVS under motion blur.
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。