We propose Strivec, a novel neural representation that models a 3D scene as a radiance field with sparsely distributed and compactly factorized local tensor feature grids. Our approach leverages tensor decomposition, following the recent work TensoRF, to model the tensor grids. In contrast to TensoRF which uses a global tensor and focuses on their vector-matrix decomposition, we propose to utilize a cloud of local tensors and apply the classic CANDECOMP/PARAFAC (CP) decomposition to factorize each tensor into triple vectors that express local feature distributions along spatial axes and compactly encode a local neural field. We also apply multi-scale tensor grids to discover the geometry and appearance commonalities and exploit spatial coherence with the tri-vector factorization at multiple local scales. The final radiance field properties are regressed by aggregating neural features from multiple local tensors across all scales. Our tri-vector tensors are sparsely distributed around the actual scene surface, discovered by a fast coarse reconstruction, leveraging the sparsity of a 3D scene. We demonstrate that our model can achieve better rendering quality while using significantly fewer parameters than previous methods, including TensoRF and Instant-NGP.

翻译：我们提出Strivec，一种新型神经表示方法，通过稀疏分布且紧凑因子化的局部张量特征网格将三维场景建模为辐射场。该方法遵循近期工作TensoRF，采用张量分解技术对张量网格进行建模。与使用全局张量并聚焦于向量-矩阵分解的TensoRF不同，我们提出利用局部张量云，并应用经典CANDECOMP/PARAFAC（CP）分解将每个张量分解为三向量——这些向量沿空间轴表达局部特征分布，并紧凑编码局部神经场。我们还采用多尺度张量网格，通过多局部尺度下的三向量因子化发现几何与外观共性，并利用空间相关性。最终辐射场属性通过聚合来自所有尺度多个局部张量的神经特征进行回归。我们的三向量张量围绕实际场景表面稀疏分布，通过快速粗重建发现，从而利用三维场景的稀疏性。实验表明，与TensoRF和Instant-NGP等先前方法相比，我们的模型能在使用显著更少参数的同时实现更优的渲染质量。