We present a machine learning approach for efficiently computing order independent transparency (OIT). Our method is fast, requires a small constant amount of memory (depends only on the screen resolution and not on the number of triangles or transparent layers), is more accurate as compared to previous approximate methods, works for every scene without setup and is portable to all platforms running even with commodity GPUs. Our method requires a rendering pass to extract all features that are subsequently used to predict the overall OIT pixel color with a pre-trained neural network. We provide a comparative experimental evaluation and shader source code of all methods for reproduction of the experiments.

翻译：本文提出一种机器学习方法，用于高效计算顺序无关透明度。该方法具有速度快、内存占用恒定（仅取决于屏幕分辨率，与三角形数量或透明层数无关）的特点，相比现有近似方法精度更高，无需场景预处理即可直接应用，且可移植至所有平台，甚至能在普通GPU上运行。该方法通过渲染通道提取全部特征，随后利用预训练神经网络预测整体顺序无关透明度像素颜色。我们提供了对比实验评估及所有方法的着色器源代码，以便复现实验结果。