Neural radiance fields (NeRFs) have achieved impressive view synthesis results by learning an implicit volumetric representation from multi-view images. To project the implicit representation into an image, NeRF employs volume rendering that approximates the continuous integrals of rays as an accumulation of the colors and densities of the sampled points. Although this approximation enables efficient rendering, it ignores the direction information in point intervals, resulting in ambiguous features and limited reconstruction quality. In this paper, we propose an anisotropic neural representation learning method that utilizes learnable view-dependent features to improve scene representation and reconstruction. We model the volumetric function as spherical harmonic (SH)-guided anisotropic features, parameterized by multilayer perceptrons, facilitating ambiguity elimination while preserving the rendering efficiency. To achieve robust scene reconstruction without anisotropy overfitting, we regularize the energy of the anisotropic features during training. Our method is flexiable and can be plugged into NeRF-based frameworks. Extensive experiments show that the proposed representation can boost the rendering quality of various NeRFs and achieve state-of-the-art rendering performance on both synthetic and real-world scenes.

翻译：神经辐射场（NeRFs）通过从多视角图像学习隐式体积表示，已取得了令人印象深刻的视图合成结果。为了将隐式表示投影到图像上，NeRF采用体渲染技术，通过将射线的连续积分近似为采样点颜色和密度的累积来实现渲染。尽管这种近似实现了高效渲染，但它忽略了点间隔中的方向信息，导致特征模糊且重建质量受限。本文提出一种各向异性神经表示学习方法，利用可学习的视角依赖特征来改进场景表示与重建。我们将体积函数建模为球谐函数（SH）引导的各向异性特征，并通过多层感知机进行参数化，从而在保持渲染效率的同时消除歧义。为实现无各向异性过拟合的鲁棒场景重建，我们在训练过程中对各向异性特征的能量进行正则化。该方法灵活且可嵌入到基于NeRF的框架中。大量实验表明，所提出的表示能提升多种NeRFs的渲染质量，并在合成场景与真实场景上均达到最先进的渲染性能。