发表机构
University of Alberta（阿尔伯塔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对风驱动植被单目重建的欠约束问题，提出物理参数化形变先验（每刚体部分阻尼谐振子），在合成测试平台上验证其物理接地性，发现其外推更优但参数恢复有限。
AI 中文摘要
单目重建风驱动植被严重欠约束：沿观察方向的运动在很大程度上不可观测，移动的树冠提供很少的可靠对应点，且几乎整个场景都是动态的，几乎没有静态参考。因此，4D高斯泼溅中直接学习的形变场优化的是光度一致性，而非恢复产生该一致性的运动。我们用物理参数化的形变先验替换该场：每个刚体部分一个阻尼谐振子，由观测到的风驱动，并通过可微RK4积分，仅由光度监督。为测试这种先验是否物理接地而非仅仅拟合良好，我们构建了一个受控的合成测试平台，包含三棵程序生成的树木，其骨架复杂度跨越一个数量级，每部分的固有频率由其自身几何决定，阻尼比是固定常数，两者均不参与训练。在该平台上，我们测量了留出视图、时间外推、对未见风速的零样本迁移以及物理参数本身的恢复。该先验在分布内视图上牺牲了外观保真度，但在训练窗口和训练风之外外推明显更好，而参数恢复远弱于其初现：频率恢复仅在三个树木中最稀疏的一个上通过了未训练的空对照，而阻尼则完全未恢复。
英文摘要
Monocular reconstruction of wind-driven vegetation is severely underconstrained: motion along the viewing direction is largely unobservable, a moving canopy offers few reliable correspondences, and nearly the entire scene is dynamic, providing little static reference. Directly-learned deformation fields in 4D Gaussian Splatting therefore optimize photometric consistency rather than recover the motion that produced it. We replace that field with a physically parameterized deformation prior: one damped harmonic oscillator per rigid part, driven by the observed wind and integrated by differentiable RK4, supervised photometrically alone. To test whether such a prior is physically grounded rather than merely well fit, we build a controlled synthetic testbed of three procedurally generated trees spanning an order of magnitude in skeleton complexity, whose per-part natural frequency follows from its own geometry and whose damping ratio is a fixed constant, both held out of training. On it, we measure held-out views, temporal extrapolation, zero-shot transfer to unseen wind speeds, and recovery of the physical parameters themselves. The prior costs appearance fidelity on in-distribution views and extrapolates markedly better outside the training window and the training wind, while parameter recovery is far weaker than it first appears: frequency recovery survives an untrained null control on only the sparsest of the three trees, and damping is not recovered at all.
CommentsWorkshop Version of ECCV 2026 3DWM Workshop
