Real-Time Neural Rasterization for Large Scenes
Jeffrey Yunfan Liu, Yun Chen, Ze Yang, Jingkang Wang, Sivabalan Manivasagam, Raquel Urtasun
Abstract
We propose a new method for realistic real-time novel-view synthesis (NVS) of large scenes. Existing neural rendering methods generate realistic results, but primarily work for small scale scenes (< 50m <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ) and have difficulty at large scale (> 10000m <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ). Traditional graphics-based rasterization rendering is fast for large scenes but lacks realism and requires expensive manually created assets. Our approach combines the best of both worlds by taking a moderate-quality scaffold mesh as input and learning a neural texture field and shader to model view-dependant effects to enhance realism, while still using the standard graphics pipeline for real-time rendering. Our method outperforms existing neural rendering methods, providing at least 30× faster rendering with comparable or better realism for large self-driving and drone scenes. Our work is the first to enable real-time rendering of large real-world scenes.