Minjung Son, Jeong Joon Park, Leonidas Guibas, Gordon Wetzstein
TL;DRSinGRAF 是一种 3D 感知的生成模型,利用一些场景的输入图像进行训练,可生成不同的 3D 场景,同时保持输入外观的不同实现。
Abstract
generative models have shown great promise in synthesizing photorealistic 3D
objects, but they require large amounts of training data. We introduce singraf,
a 3D-aware generative model that is trained with a few