论文标题
gendr：广义可区分的渲染器
GenDR: A Generalized Differentiable Renderer
论文作者
论文摘要
在这项工作中，我们介绍并研究了一个普遍的可区分渲染器家族。我们从头开始讨论哪些组件对于可区分渲染和正式化每个组件的要求是必要的。我们实例化了我们的一般可区分渲染器，该渲染器概括了现有的可区分渲染器，例如SOFTRAS和DIB-R，并具有一系列不同的平滑分布，以涵盖各种合理的设置。我们在流行的Shapenet 3D重建基准上评估了一系列可区分的渲染器实例，并分析了我们结果的含义。令人惊讶的是，当平均13个类别的平均值时，简单的均匀分布会产生最佳的总体结果。但是，通常，分配的最佳选择在很大程度上取决于任务。
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.
