Deblur4DGS：从模糊单目视频中进行4D高斯散射
Deblur4DGS: 4D Gaussian Splatting from Blurry Monocular Video
AI总结：
Deblur4DGS通过引入曝光正则化和多分辨率一致性正则化，从模糊单目视频中高质量重建4D模型，提升视频去模糊、帧插值和稳定效果。
摘要：
最近的4D重建方法取得了令人印象深刻的结果，但依赖于清晰的视频作为监督。然而，由于相机抖动和物体运动，视频中经常会出现运动模糊，而现有方法在使用此类视频重建4D模型时会产生模糊结果。尽管已有少数方法尝试解决这个问题，但它们难以产生高质量的结果，因为连续动态表示在曝光时间内估计不准确。受近期使用3D高斯散射（3DGS）进行3D运动轨迹建模的工作启发，我们将3DGS作为场景表示方法，并提出Deblur4DGS，从模糊的单目视频中重建高质量的4D模型。具体而言，我们将曝光时间内连续动态表示的估计转换为曝光时间估计。此外，我们引入了曝光正则化项、多帧和多分辨率一致性正则化项，以避免平凡解。此外，为了更好地表示大运动物体，我们建议引入模糊感知的变量规范高斯分布。除了新颖视角合成外，Deblur4DGS还可以用于从多个视角改善模糊视频，包括去模糊、帧插值和视频稳定。在合成和现实数据上对上述四项任务进行了广泛的实验，结果表明Deblur4DGS优于最先进的4D重建方法。代码可在https://github.com/ZcsrenlongZ/Deblur4DGS上获得。
英文摘要：
Recent 4D reconstruction methods have yielded impressive results but rely on sharp videos as supervision. However, motion blur often occurs in videos due to camera shake and object movement, while existing methods render blurry results when using such videos for reconstructing 4D models. Although a few approaches attempted to address the problem, they struggled to produce high-quality results, due to the inaccuracy in estimating continuous dynamic representations within the exposure time. Encouraged by recent works in 3D motion trajectory modeling using 3D Gaussian Splatting (3DGS), we take 3DGS as the scene representation manner, and propose Deblur4DGS to reconstruct a high-quality 4D model from blurry monocular video. Specifically, we transform continuous dynamic representations estimation within an exposure time into the exposure time estimation. Moreover, we introduce the exposure regularization term, multi-frame, and multi-resolution consistency regularization term to avoid trivial solutions. Furthermore, to better represent objects with large motion, we suggest blur-aware variable canonical Gaussians. Beyond novel-view synthesis, Deblur4DGS can be applied to improve blurry video from multiple perspectives, including deblurring, frame interpolation, and video stabilization. Extensive experiments in both synthetic and real-world data on the above four tasks show that Deblur4DGS outperforms state-of-the-art 4D reconstruction methods. The codes are available at https://github.com/ZcsrenlongZ/Deblur4DGS.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
