Neural Frame Interpolation for Rendered Content

The demand for creating rendered content continues to drastically grow. As it often is extremely computationally expensive and thus costly to render highquality computer generated images, there is a high incentive to reduce this computational burden. Recent advances in learningbased frame interpolation methods have shown exciting progress but still have not achieved the productionlevel quality which would be required to render less pixels and achieve savings in rendering times and costs. Therefore, in this paper we propose a method specifically targeted to achieve high quality frame interpolation for rendered content. In this setting, we assume that we have full input every nth frame in addition to auxiliary feature buffers that are cheap to evaluate depth, normals, albedo) for every frame. We propose solutions for leveraging such auxiliary features to obtain better motion estimates, more accurate occlusion handling, and to correctly reconstruct nonlinear motion between keyframes. With this our m