Primitive-based methods such as 3D Gaussian Splatting have recently become the state-of-the-art for novel-view synthesis and related reconstruction tasks. Compared to neural fields, these representations are more flexible, adaptive, and scale better to large scenes. However, the limited expressivity of individual primitives makes modeling high-frequency detail challenging. We introduce Neural Harmonic Textures, a neural representation approach that anchors latent feature vectors on a virtual scaffold surrounding each primitive. These features are interpolated within the primitive at ray intersection points. Inspired by Fourier analysis, we apply periodic activations to the interpolated features, turning alpha blending into a weighted sum of harmonic components. The resulting signal is then decoded in a single deferred pass using a small neural network, significantly reducing computational cost. Neural Harmonic Textures yield state-of-the-art results in real-time novel view synthesis while bridging the gap between primitive- and neural-field-based reconstruction. Our method integrates seamlessly into existing primitive-based pipelines such as 3DGUT, Triangle Splatting, and 2DGS. We further demonstrate its generality with applications to 2D image fitting and semantic reconstruction.

翻译：基于基元的方法（如3D高斯泼溅）近期已成为新视角合成及相关重建任务的最先进技术。与神经场相比，这类表示更具灵活性与自适应性，且能更好地扩展到大规模场景。然而，单个基元的有限表达能力使得高频细节的建模面临挑战。我们提出神经谐波纹理，这是一种神经表示方法，将潜特征向量锚定在每个基元周围的虚拟支架上。这些特征在光线与基元的交点处被插值。受傅里叶分析启发，我们对插值后的特征应用周期激活，将阿尔法混合转化为谐波分量的加权求和。所得信号随后通过一个小型神经网络以单次延迟解码方式处理，显著降低计算成本。神经谐波纹理在实时新视角合成中取得了最先进成果，同时弥合了基于基元与基于神经场的重建之间的差距。我们的方法能无缝集成到现有基元管线（如3DGUT、三角泼溅和2DGS）中，并通过二维图像拟合与语义重建应用进一步证明了其通用性。