InfoGaussian：通过轻量级信息塑形实现结构感知的动态Gaussians
InfoGaussian: Structure-Aware Dynamic Gaussians through Lightweight Information Shaping
AI总结：
针对3D Gaussians难以反映底层动态结构的问题，提出互信息塑形技术，通过运动Jacobian近似和轻量级对比训练，在运动网络中强制相关Gaussians运动共振，实现高效一致的运动控制与3D物体分割。
摘要：
3D Gaussians作为一种低级场景表示，通常包含数千至数百万个Gaussians。这使得以反映底层动态结构的方式控制场景变得困难，因为底层独立实体的数量通常要少得多。特别是，在场景中对物体进行动画处理和移动可能具有挑战性，因为这需要许多Gaussians之间的协调。为了解决这个问题，我们开发了一种互信息塑形技术，在运动网络中强制相关Gaussians之间的运动共振。这种相关性可以从不同视图中的假定2D物体掩码中学习。通过用运动的Jacobian近似互信息，我们的方法确保在各种扰动下组成不同物体的Gaussians的运动一致性。特别是，我们开发了一个带有轻量级优化的高效对比训练管道来塑形运动网络，避免了在整个运动序列中重新塑形的需要。值得注意的是，我们的训练仅触及场景中所有Gaussians的一小部分，却根据底层动态结构获得了所需的组合行为。所提出的技术在具有挑战性的场景上进行了评估，并在促进一致运动和3D物体分割方面表现出显著的性能提升，同时具有低计算和内存需求。
英文摘要：
3D Gaussians, as a low-level scene representation, typically involve thousands to millions of Gaussians. This makes it difficult to control the scene in ways that reflect the underlying dynamic structure, where the number of independent entities is typically much smaller. In particular, it can be challenging to animate and move objects in the scene, which requires coordination among many Gaussians. To address this issue, we develop a mutual information shaping technique that enforces movement resonance between correlated Gaussians in a motion network. Such correlations can be learned from putative 2D object masks in different views. By approximating the mutual information with the Jacobians of the motions, our method ensures consistent movements of the Gaussians composing different objects under various perturbations. In particular, we develop an efficient contrastive training pipeline with lightweight optimization to shape the motion network, avoiding the need for re-shaping throughout the motion sequence. Notably, our training only touches a small fraction of all Gaussians in the scene yet attains the desired compositional behavior according to the underlying dynamic structure. The proposed technique is evaluated on challenging scenes and demonstrates significant performance improvement in promoting consistent movements and 3D object segmentation while inducing low computation and memory requirements.
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。
