运动感知的可动画高斯化身去模糊
Motion-Aware Animatable Gaussian Avatars Deblurring
提出一种基于物理的运动模糊形成模型，结合3D人体运动模型，从模糊多视角视频中联合优化高斯化身表示与运动参数，为动态场景重建中的运动模糊问题提供可复用思路。
原文依据 This paper introduces a novel method for directly reconstructing sharp 3D human Gaussian avatars from blurry videos.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从多视角视频创建3D人体化身是计算机视觉中一项重要但具有挑战性的任务。然而，现有技术依赖高质量、清晰的图像作为输入，而在真实场景中，由于人体运动速度和强度的变化，这类图像往往难以获取。本文提出一种新方法，可直接从模糊视频中重建清晰的三维人体高斯化身。该方法结合了基于物理的、三维感知的人体运动模糊形成模型，以及一个旨在解决运动诱导模糊歧义的三维人体运动模型。该框架能够从粗略初始化开始，联合优化化身表示与运动参数。我们使用合成数据集和通过360度同步混合曝光相机系统采集的真实世界数据集建立了全面的基准。大量评估表明，该模型在不同条件下均有效。代码见：https://github.com/MyNiuuu/MAD-Avatar
英文原文摘要 1065 字符
The creation of 3D human avatars from multi-view videos is a significant yet challenging task in computer vision. However, existing techniques rely on high-quality, sharp images as input, which are often impractical to obtain in real-world scenarios due to variations in human motion speed and intensity. This paper introduces a novel method for directly reconstructing sharp 3D human Gaussian avatars from blurry videos. The proposed approach incorporates a 3D-aware, physics-based model of blur formation caused by human motion, together with a 3D human motion model designed to resolve ambiguities in motion-induced blur. This framework enables the joint optimization of the avatar representation and motion parameters from a coarse initialization. Comprehensive benchmarks are established using both a synthetic dataset and a real-world dataset captured with a 360-degree synchronous hybrid-exposure camera system. Extensive evaluations demonstrate the effectiveness of the model across diverse conditions. Codes Available: https://github.com/MyNiuuu/MAD-Avatar