论文标题
LetentsWap3D：3D图像gans上的语义编辑
LatentSwap3D: Semantic Edits on 3D Image GANs
论文作者
论文摘要
3D GAN具有为整个3D卷而不是仅2D图像生成潜在代码的能力。这些模型提供了理想的功能，例如高质量的几何形状和多视图一致性，但是，与他们的2D对应物不同，仅探索了3D GAN的复杂语义图像编辑任务。为了解决这个问题，我们建议LetantWap3D，这是一种基于潜在空间发现的语义编辑方法，可以与任何现成的3D或2D GAN模型以及任何数据集一起使用。 LetentsWap3D依赖于使用随机森林分类器进行排名来识别与特定属性相对应的潜在代码尺寸。然后，它通过与自动选择的参考图像中的图像的所选尺寸交换所选的尺寸来执行编辑。与其他主要是为2D GAN设计的潜在潜在空间控制方法相比，我们的3D GAN上的方法以分离的方式提供了非常一致的语义编辑，并且在定性和定量上都胜过其他人。我们显示了七个3D GAN（Pi-Gan，长颈鹿，StylesDF，MVCGAN，EG3D，StyLenerf和volumegan）以及五个数据集（FFHQ，AFHQ，CAT，METFACES和COMPCARS）的结果。
3D GANs have the ability to generate latent codes for entire 3D volumes rather than only 2D images. These models offer desirable features like high-quality geometry and multi-view consistency, but, unlike their 2D counterparts, complex semantic image editing tasks for 3D GANs have only been partially explored. To address this problem, we propose LatentSwap3D, a semantic edit approach based on latent space discovery that can be used with any off-the-shelf 3D or 2D GAN model and on any dataset. LatentSwap3D relies on identifying the latent code dimensions corresponding to specific attributes by feature ranking using a random forest classifier. It then performs the edit by swapping the selected dimensions of the image being edited with the ones from an automatically selected reference image. Compared to other latent space control-based edit methods, which were mainly designed for 2D GANs, our method on 3D GANs provides remarkably consistent semantic edits in a disentangled manner and outperforms others both qualitatively and quantitatively. We show results on seven 3D GANs (pi-GAN, GIRAFFE, StyleSDF, MVCGAN, EG3D, StyleNeRF, and VolumeGAN) and on five datasets (FFHQ, AFHQ, Cats, MetFaces, and CompCars).
