Recent research on learnable neural representations has been widely adopted in the field of 3D scene reconstruction and neural rendering applications. However, traditional feature grid representations often suffer from substantial memory footprint, posing a significant bottleneck for modern parallel computing hardware. In this paper, we present neural vertex features, a generalized formulation of learnable representation for neural rendering tasks involving explicit mesh surfaces. Instead of uniformly distributing neural features throughout 3D space, our method stores learnable features directly at mesh vertices, leveraging the underlying geometry as a compact and structured representation for neural processing. This not only optimizes memory efficiency, but also improves feature representation by aligning compactly with the surface using task-specific geometric priors. We validate our neural representation across diverse neural rendering tasks, with a specific emphasis on neural radiosity. Experimental results demonstrate that our method reduces memory consumption to only one-fifth (or even less) of grid-based representations, while maintaining comparable rendering quality and lowering inference overhead.

翻译：关于可学习神经表示的最新研究已被广泛应用于三维场景重建与神经渲染应用领域。然而，传统特征网格表示往往存在显著的内存占用问题，这成为现代并行计算硬件的主要瓶颈。本文提出了神经顶点特征，这是一种面向涉及显式网格表面的神经渲染任务的可学习表示的通用公式化方法。不同于在三维空间中均匀分布神经特征，本方法将可学习特征直接存储于网格顶点，利用底层几何结构作为紧凑且结构化的神经处理表示。这不仅优化了内存效率，还通过利用任务特定的几何先验使特征表示与表面对齐，从而提升了表示质量。我们在多种神经渲染任务中验证了所提神经表示的有效性，并特别聚焦于神经辐射度方法。实验结果表明，本方法的内存消耗降至网格表示的五分之一（甚至更少），同时保持可比的渲染质量并降低推理开销。