论文标题
SDF-STYLEGAN：3D形状的隐性基于SDF的stylegan
SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation
论文作者
论文摘要
我们为3D形状生成（称为SDF-Stylegan）提供了一种基于StyleGAN的深度学习方法，目的是减少生成形状和形状集合之间的视觉和几何差异。我们将StyleGAN2扩展到3D代，并利用隐式签名的距离函数（SDF）作为3D形状表示，并引入了两个新颖的全球和局部形状鉴别器，它们区分了真实和假的SDF值和梯度，以显着提高形状的几何形状和视觉质量。我们进一步补充了3D生成模型的评估指标，其基于阴影图像的FRéchet成立距离（FID）得分可以更好地评估所产生形状的视觉质量和形状分布。对形状生成的实验证明了SDF-Stylegan的表现优于最先进的。我们进一步证明了基于GAN倒置的各种任务中SDF-Stylegan的功效，包括形状重建，部分点云的形状完成，基于单图像的形状形状生成以及形状样式编辑。广泛的消融研究证明了我们的框架设计的功效。我们的代码和训练有素的模型可在https://github.com/zhengxinyang/sdf-stylegan上找到。
We present a StyleGAN2-based deep learning approach for 3D shape generation, called SDF-StyleGAN, with the aim of reducing visual and geometric dissimilarity between generated shapes and a shape collection. We extend StyleGAN2 to 3D generation and utilize the implicit signed distance function (SDF) as the 3D shape representation, and introduce two novel global and local shape discriminators that distinguish real and fake SDF values and gradients to significantly improve shape geometry and visual quality. We further complement the evaluation metrics of 3D generative models with the shading-image-based Fréchet inception distance (FID) scores to better assess visual quality and shape distribution of the generated shapes. Experiments on shape generation demonstrate the superior performance of SDF-StyleGAN over the state-of-the-art. We further demonstrate the efficacy of SDF-StyleGAN in various tasks based on GAN inversion, including shape reconstruction, shape completion from partial point clouds, single-view image-based shape generation, and shape style editing. Extensive ablation studies justify the efficacy of our framework design. Our code and trained models are available at https://github.com/Zhengxinyang/SDF-StyleGAN.
