D-MiSo：使用多高斯汤编辑动态3D场景
D-MiSo: Editing Dynamic 3D Scenes using Multi-Gaussians Soup
AI总结：
针对动态3D场景编辑的挑战，提出D-MiSo方法，通过网格启发式多高斯汤表示及三角汤构建策略，实现场景中3D对象轨迹的单独编辑，解决了现有方法需手动选择固定元素和质心、可复现性差的问题。
摘要：
过去几年，我们见证了大量使用高斯溅射（GS）对动态3D场景进行建模的方法。这类方案利用GS表示场景结构，用神经网络建模动态，可实现快速渲染并提取动态场景的每个元素。但随时间修改这类对象具有挑战性。SC-GS（稀疏控制高斯溅射）结合变形控制点部分解决了该问题，但需选择需固定的元素及编辑过程中需调整的质心，且在编辑可复现性方面存在额外困难。为此，我们提出动态多高斯汤（D-MiSo），可对动态GS进行网格启发式表示建模；还提出连接参数化高斯溅射的策略，结合估计网格形成三角汤，从而为场景中的3D对象单独构建新轨迹，使场景动态可随时间编辑或保持部分动态。
英文摘要：
Over the past years, we have observed an abundance of approaches for modeling dynamic 3D scenes using Gaussian Splatting (GS). Such solutions use GS to represent the scene's structure and the neural network to model dynamics. Such approaches allow fast rendering and extracting each element of such a dynamic scene. However, modifying such objects over time is challenging. SC-GS (Sparse Controlled Gaussian Splatting) enhanced with Deformed Control Points partially solves this issue. However, this approach necessitates selecting elements that need to be kept fixed, as well as centroids that should be adjusted throughout editing. Moreover, this task poses additional difficulties regarding the re-productivity of such editing. To address this, we propose Dynamic Multi-Gaussian Soup (D-MiSo), which allows us to model the mesh-inspired representation of dynamic GS. Additionally, we propose a strategy of linking parameterized Gaussian splats, forming a Triangle Soup with the estimated mesh. Consequently, we can separately construct new trajectories for the 3D objects composing the scene. Thus, we can make the scene's dynamic editable over time or while maintaining partial dynamics.
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。
