In this work, we present and study a generalized family of differentiable
renderers. We discuss from scratch which components are necessary for
differentiable rendering and formalize the requirements for each component. We
instantiate our general differentiable renderer, which generalizes existing
differentiable renderers like SoftRas and DIB-R, with an array of different
smoothing distributions to cover a large spectrum of reasonable settings. We
evaluate an array of differentiable renderer instantiations on the popular
ShapeNet 3D reconstruction benchmark and analyze the implications of our
results. Surprisingly, the simple uniform distribution yields the best overall
results when averaged over 13 classes; in general, however, the optimal choice
of distribution heavily depends on the task.

本文研究了可微分渲染器相关的各个基础组件的需求，提出了一种广义的可微分渲染器，并利用不同的平滑分布进行了实例化，通过在 ShapeNet 3D 重建基准测试上的多种尝试，分析了结果的影响。令人惊讶的是，在 13 个类别中的平均结果上，简单的均匀分布效果最好；然而，通常来说，最佳的分布选择很大程度上取决于任务。