In view synthesis, a neural radiance field approximates underlying density and radiance fields based on a sparse set of scene pictures. To generate a pixel of a novel view, it marches a ray through the pixel and computes a weighted sum of radiance emitted from a dense set of ray points. This rendering algorithm is fully differentiable and facilitates gradient-based optimization of the fields. However, in practice, only a tiny opaque portion of the ray contributes most of the radiance to the sum. We propose an end-to-end differentiable sampling algorithm based on inverse transform sampling. It generates samples according to the probability distribution induced by the density field and picks non-transparent points on the ray. We utilize the algorithm in two ways. First, we propose a novel rendering approach based on Monte Carlo estimates. Such a rendering algorithm allows for optimizing a neural radiance field with just a few radiance field evaluations per ray. Second, we use the sampling algorithm to modify the hierarchical scheme used in the original work on neural radiance fields. In this setup, we were able to train the proposal network end-to-end without any auxiliary losses and improved the baseline performance.
翻译:合成时, 神经弧度字段根据一组稀少的场景图片, 近似于下面的密度和亮度字段。 为了生成新视图的像素, 它在像素中进行射线, 并计算出一组稠密的射线点所释放的弧度加权数。 这种转换算法是完全不同的, 便于对字段进行梯度优化。 然而, 实际上, 光线中只有很小的不透明部分能贡献大部分亮度。 我们提议了一个基于反向变换抽样的端到端的不同取样算法。 它根据密度字段所引发的概率分布生成样本, 在射线上选取非透明点。 我们用两种方式使用算法。 首先, 我们提出一个基于蒙特卡洛估计的新的表达法。 这种转换算法可以优化一个神经弧度字段, 并且每个射线只进行少量的亮度场评价。 其次, 我们使用取样算法来修改最初在神经光亮度域工作中使用的等级方案。 在此设置下, 我们能够对建议网络的端端端端端端到端点性进行训练, 没有任何辅助性损失。