用于实时可重位姿动态视图合成的无模板铰接式高斯溅射
Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesis
AI总结：
针对动态场景中对象骨架模型捕获与重位姿难题，提出无模板铰接式高斯溅射方法，结合三维高斯溅射与超点重建动态对象、发现并优化骨架，通过自适应策略避免冗余超点，实现高保真可重位姿三维对象获取与实时高分辨率渲染。
摘要：
尽管动态场景的新视图合成已取得显著进展，但捕获对象的骨架模型并对其进行重位姿仍然是一项具有挑战性的任务。为解决该问题，本文提出了一种新方法，无需对象特定模板即可从视频中自动发现动态对象的关联骨架模型。该方法利用3D Gaussian Splatting（三维高斯溅射）和superpoints（超点）重建动态对象。将超点视为刚性部件，可通过直观线索发现底层骨架模型，并使用运动学模型对其进行优化。此外，还采用了自适应控制策略以避免出现冗余超点。大量实验证明了该方法在获取可重位姿三维对象方面的有效性与高效性，不仅能实现出色的视觉保真度，还支持高分辨率图像的实时渲染。
英文摘要：
While novel view synthesis for dynamic scenes has made significant progress, capturing skeleton models of objects and re-posing them remains a challenging task. To tackle this problem, in this paper, we propose a novel approach to automatically discover the associated skeleton model for dynamic objects from videos without the need for object-specific templates. Our approach utilizes 3D Gaussian Splatting and superpoints to reconstruct dynamic objects. Treating superpoints as rigid parts, we can discover the underlying skeleton model through intuitive cues and optimize it using the kinematic model. Besides, an adaptive control strategy is applied to avoid the emergence of redundant superpoints. Extensive experiments demonstrate the effectiveness and efficiency of our method in obtaining re-posable 3D objects. Not only can our approach achieve excellent visual fidelity, but it also allows for the real-time rendering of high-resolution images.
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。
