SurfGen: Adversarial 3D Shape Synthesis with Explicit Surface Discriminators
SurfGen: Adversarial 3D Shape Synthesis with Explicit Surface Discriminators
复制标题
DOI：
10.1109/iccv48922.2021.01593
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Andrew Luo;Tianqin Li;Wenhao Zhang;T. Lee
中科院分区：
文献类型：
--
作者：
Andrew Luo;Tianqin Li;Wenhao Zhang;T. Lee
深度生成模型的最新进展导致了3D形状合成的巨大进步。虽然现有的模型能够合成表示为体素，点云，或隐式函数的形状，这些方法只能间接地执行最终的三维形状表面的可扩展性。在这里，我们提出了一个3D形状合成框架（SurfGen），它直接将对抗训练应用于对象表面。我们的方法使用可微球面投影层来捕获和表示隐式3D生成器的显式零等值面作为单位球面上定义的函数。通过在对抗设置中使用球形CNN处理3D对象表面的球形表示，我们的生成器可以更好地学习自然形状表面的统计数据。我们在大规模形状数据集上评估了我们的模型，并证明了端到端训练模型能够生成具有不同拓扑结构的高保真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.