This paper proposes a neural radiance field (NeRF) approach for novel view synthesis of dynamic scenes using forward warping. Existing methods often adopt a static NeRF to represent the canonical space, and render dynamic images at other time steps by mapping the sampled 3D points back to the canonical space with the learned backward flow field. However, this backward flow field is non-smooth and discontinuous, which is difficult to be fitted by commonly used smooth motion models. To address this problem, we propose to estimate the forward flow field and directly warp the canonical radiance field to other time steps. Such forward flow field is smooth and continuous within the object region, which benefits the motion model learning. To achieve this goal, we represent the canonical radiance field with voxel grids to enable efficient forward warping, and propose a differentiable warping process, including an average splatting operation and an inpaint network, to resolve the many-to-one and one-to-many mapping issues. Thorough experiments show that our method outperforms existing methods in both novel view rendering and motion modeling, demonstrating the effectiveness of our forward flow motion modeling. Project page: https://npucvr.github.io/ForwardFlowDNeRF

翻译：本文提出一种基于神经辐射场（NeRF）的前向扭曲方法，用于动态场景的新视角合成。现有方法通常采用静态NeRF表示规范空间，并通过学习到的后向光流将采样三维点映射回规范空间，从而渲染其他时刻的动态图像。然而，这种后向光流场非平滑且不连续，难以被常用的平滑运动模型拟合。为解决该问题，我们提出估计前向光流场，并直接将规范辐射场扭曲至其他时刻。这种前向光流场在物体区域内平滑连续，有利于运动模型的学习。为实现目标，我们采用体素网格表示规范辐射场以支持高效前向扭曲，并提出包含平均喷溅操作和修复网络的可微分扭曲过程，以解决多对一与一对多的映射问题。大量实验表明，本方法在新视角渲染与运动建模方面均优于现有方法，验证了所提前向光流运动建模的有效性。项目主页：https://npucvr.github.io/ForwardFlowDNeRF