LagrangianSplats: 用于流体重建的无散度传输高斯原语
LagrangianSplats: Divergence-Free Transport of Gaussian Primitives for Fluid Reconstruction
AI总结:
本文提出一种基于无散度核的框架,通过拉格朗日3D高斯点散布实现流体重建,确保流体不可压缩性和远距离传输一致性,实验显示其在传输一致性和物理准确性上优于现有方法。
摘要:
从稀疏2D视频观测中重建3D流体速度场是一个高度病态的逆问题,需要同时满足传输一致性和流体定律的物理有效性。现有方法通常通过软惩罚施加这些约束,导致精度下降和收敛问题。本文提出一个结构上强制这些约束的重建框架。具体来说,我们用连续的无散度核表示重建速度,驱动拉格朗日3D高斯点散布的输运。这种形式通过构造保证流体不可压缩性和远距离传输一致性。为高效优化此类约束系统,我们引入了新的滑动窗口方案,在保持可训练成本的同时传播梯度以覆盖有意义的时间范围。在合成和真实数据集上的实验表明,我们的方法在传输一致性和物理准确性上优于现有方法,实现了高质量的重新模拟和流体分析。
英文摘要:
Reconstructing 3D fluid velocity fields from sparse 2D video observations is a highly ill-posed inverse problem, demanding both transport consistency with observed motion and physical validity under fluid laws. Existing methods typically impose these constraints through soft penalties, often leading to compromised accuracy and convergence issues. We introduce a reconstruction framework that structurally enforces both constraints. Specifically, we parameterize the reconstructed velocity using a continuous Divergence-Free Kernel representation, driving the advection of a Lagrangian 3D Gaussian Splatting representation. This formulation intrinsically guarantees both flow incompressibility and long-range transport coherence by construction. To enable the efficient optimization of such a constrained system, we introduce a novel Sliding Window scheme that propagates gradients over meaningful temporal horizons while maintaining tractable training costs. Experiments on synthetic and real-world datasets demonstrate that our method outperforms state-of-the-art baselines in both transport consistency and physical accuracy, enabling applications such as high-quality re-simulation and flow analysis.
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。