论文标题
连续动态-NERF：样条杆
Continuous Dynamic-NeRF: Spline-NeRF
论文作者
论文摘要
随着时间的流逝，重建连续功能的问题对于重建移动场景以及在时间步长之间插值等问题很重要。使用深度学习的先前方法依赖于正规化来确保重建大致连续，这在短序列上效果很好。但是，随着序列长度的增长，正规化变得更加困难，并且仅通过正规化学习就变得不那么可行。我们为基于经典的bezier花键提出了一种用于功能重建的新体系结构，可确保$ c^0 $和$ c^1 $ -continuity，其中$ c^0 $连续性是$ \ forall c：\ lim \ limists_ {x \ to c} f（x）f（x）f（x）f（x） = f（c）$，或更直观地认为该功能的任何时刻都没有断裂。为了展示我们的体系结构，我们使用神经辐射场重建动态场景，但希望我们的方法很清楚，可以应用于各种问题。我们恢复了由控制点$β$参数的bezier样条$ b（β，t \ in [0,1]）$。使用Bezier花纹确保重建具有$ C^0 $和$ C^1 $连续性，可以随着时间的推移提供保证的插值。我们使用多层感知器（MLP），将机器学习与经典动画技术重建$β$。所有代码均可在https://github.com/julianknnodt/nerf_atlas上找到，数据集来自先前的工作。
The problem of reconstructing continuous functions over time is important for problems such as reconstructing moving scenes, and interpolating between time steps. Previous approaches that use deep-learning rely on regularization to ensure that reconstructions are approximately continuous, which works well on short sequences. As sequence length grows, though, it becomes more difficult to regularize, and it becomes less feasible to learn only through regularization. We propose a new architecture for function reconstruction based on classical Bezier splines, which ensures $C^0$ and $C^1$-continuity, where $C^0$ continuity is that $\forall c:\lim\limits_{x\to c} f(x) = f(c)$, or more intuitively that there are no breaks at any point in the function. In order to demonstrate our architecture, we reconstruct dynamic scenes using Neural Radiance Fields, but hope it is clear that our approach is general and can be applied to a variety of problems. We recover a Bezier spline $B(β, t\in[0,1])$, parametrized by the control points $β$. Using Bezier splines ensures reconstructions have $C^0$ and $C^1$ continuity, allowing for guaranteed interpolation over time. We reconstruct $β$ with a multi-layer perceptron (MLP), blending machine learning with classical animation techniques. All code is available at https://github.com/JulianKnodt/nerf_atlas, and datasets are from prior work.
