论文标题
Surfgen：具有显式表面歧视器的对抗性3D形状合成
SurfGen: Adversarial 3D Shape Synthesis with Explicit Surface Discriminators
论文作者
论文摘要
深层生成模型的最新进展导致了3D形状合成的巨大进步。尽管现有模型能够合成表示为体素，点云或隐式功能的形状，但这些方法仅间接地强制执行最终3D形状表面的合理性。在这里，我们提出了一个3D形状的合成框架（Surfgen），该框架直接将对抗训练应用于对象表面。我们的方法使用一个可区分的球形投影层来捕获并表示隐式3D生成器的显式零等于零，如在单位球体上定义的函数。通过在对抗环境中使用球形CNN处理3D对象表面的球形表示，我们的发电机可以更好地学习自然形状表面的统计数据。我们在大型形状数据集上评估了我们的模型，并证明了端到端训练的模型能够生成具有不同拓扑的高保真3D形状。
Recent advances in deep generative models have led to immense progress in 3D shape synthesis. While existing models are able to synthesize shapes represented as voxels, point-clouds, or implicit functions, these methods only indirectly enforce the plausibility of the final 3D shape surface. Here we present a 3D shape synthesis framework (SurfGen) that directly applies adversarial training to the object surface. Our approach uses a differentiable spherical projection layer to capture and represent the explicit zero isosurface of an implicit 3D generator as functions defined on the unit sphere. By processing the spherical representation of 3D object surfaces with a spherical CNN in an adversarial setting, our generator can better learn the statistics of natural shape surfaces. We evaluate our model on large-scale shape datasets, and demonstrate that the end-to-end trained model is capable of generating high fidelity 3D shapes with diverse topology.
