Recent works use the Neural radiance field (NeRF) to perform multi-view 3D reconstruction, providing a significant leap in rendering photorealistic scenes. However, despite its efficacy, NeRF exhibits limited capability of learning view-dependent effects compared to light field rendering or image-based view synthesis. To that end, we introduce a modification to the NeRF rendering equation which is as simple as a few lines of code change for any NeRF variations, while greatly improving the rendering quality of view-dependent effects. By swapping the integration operator and the direction decoder network, we only integrate the positional features along the ray and move the directional terms out of the integration, resulting in a disentanglement of the view-dependent and independent components. The modified equation is equivalent to the classical volumetric rendering in ideal cases on object surfaces with Dirac densities. Furthermore, we prove that with the errors caused by network approximation and numerical integration, our rendering equation exhibits better convergence properties with lower error accumulations compared to the classical NeRF. We also show that the modified equation can be interpreted as light field rendering with learned ray embeddings. Experiments on different NeRF variations show consistent improvements in the quality of view-dependent effects with our simple modification.

翻译：近期研究利用神经辐射场（NeRF）进行多视图三维重建，在渲染逼真场景方面取得了重大突破。然而，尽管NeRF效果显著，但与光场渲染或基于图像的视图合成相比，其在学习视角依赖效应方面能力有限。为此，我们提出了一种对NeRF渲染方程的修改，该修改仅需在任意NeRF变体中进行少量代码改动，却能大幅提升视角依赖效应的渲染质量。通过交换积分算子与方向解码器网络，我们仅沿光线对位置特征进行积分，并将方向项移出积分过程，从而实现了视角依赖与视角独立分量的解耦。在具有狄拉克密度的物体表面理想情况下，修改后的方程等价于经典体渲染。此外，我们证明，由于网络近似和数值积分导致的误差，相较于经典NeRF，我们的渲染方程具有更好的收敛特性以及更低的误差累积。同时，我们还表明修改后的方程可解释为基于学习光线嵌入的光场渲染。在不同NeRF变体上的实验一致表明，这一简单修改显著提升了视角依赖效应的渲染质量。