论文标题
d-tensorf：动态场景的紧张辐射场
D-TensoRF: Tensorial Radiance Fields for Dynamic Scenes
论文作者
论文摘要
神经辐射场（NERF）吸引了人们的关注，作为重建3D场景的一种有前途的方法。随着NERF的出现，已经进行了随后的研究，以模拟动态场景，其中包括运动或拓扑变化。但是，他们中的大多数都使用额外的变形网络，从而降低了训练和渲染速度。张力辐射场（Tensorf）最近显示了其对具有紧凑模型大小的静态场景快速，高质量重建的潜力。在本文中，我们介绍了D-Tensorf，这是一个用于动态场景的张力辐射场，在特定时间启用了新型视图合成。我们将动态场景的辐射场视为5D张量。 5D张量表示每个轴对应于X，Y，Z和时间的4D网格，并且每个元素具有1D多通道特征。与Tensorf相似，我们将网格分解为等级的矢量成分（CP分解）或低升压矩阵组件（新提出的MM分解）。我们还使用平滑正则化来反映不同时间（时间依赖性）的特征之间的关系。我们进行广泛的评估以分析我们的模型。我们表明，与3D动态场景建模中的最新方法相比，与CP分解和MM分解的D-Tensorf具有较短的训练时间和明显较低的记忆足迹。
Neural radiance field (NeRF) attracts attention as a promising approach to reconstructing the 3D scene. As NeRF emerges, subsequent studies have been conducted to model dynamic scenes, which include motions or topological changes. However, most of them use an additional deformation network, slowing down the training and rendering speed. Tensorial radiance field (TensoRF) recently shows its potential for fast, high-quality reconstruction of static scenes with compact model size. In this paper, we present D-TensoRF, a tensorial radiance field for dynamic scenes, enabling novel view synthesis at a specific time. We consider the radiance field of a dynamic scene as a 5D tensor. The 5D tensor represents a 4D grid in which each axis corresponds to X, Y, Z, and time and has 1D multi-channel features per element. Similar to TensoRF, we decompose the grid either into rank-one vector components (CP decomposition) or low-rank matrix components (newly proposed MM decomposition). We also use smoothing regularization to reflect the relationship between features at different times (temporal dependency). We conduct extensive evaluations to analyze our models. We show that D-TensoRF with CP decomposition and MM decomposition both have short training times and significantly low memory footprints with quantitatively and qualitatively competitive rendering results in comparison to the state-of-the-art methods in 3D dynamic scene modeling.
