Previous approaches to generate shapes in a 3D setting train a GAN on the latent space of an autoencoder (AE). Even though this produces convincing results, it has two major shortcomings. As the GAN is limited to reproduce the dataset the AE was trained on, we cannot reuse a trained AE for novel data. Furthermore, it is difficult to add spatial supervision into the generation process, as the AE only gives us a global representation. To remedy these issues, we propose to train the GAN on grids (i.e. each cell covers a part of a shape). In this representation each cell is equipped with a latent vector provided by an AE. This localized representation enables more expressiveness (since the cell-based latent vectors can be combined in novel ways) as well as spatial control of the generation process (e.g. via bounding boxes). Our method outperforms the current state of the art on all established evaluation measures, proposed for quantitatively evaluating the generative capabilities of GANs. We show limitations of these measures and propose the adaptation of a robust criterion from statistical analysis as an alternative.
翻译:在3D 设置一个自动编码器(AE)潜在空间的 GAN 培训中生成形状的先前方法。 尽管这能产生令人信服的结果, 但它有两大缺点。 由于GAN 仅限于复制AE培训过的数据集, 我们不能再将受过训练的 AE 用于新数据。 此外, 在生成过程中增加空间监督是困难的, 因为 AE 只能给我们一个全球代表性。 为了解决这些问题, 我们提议在网格上培训GAN (即每个单元格覆盖一个形状的一部分) 。 在此表示中, 每个单元格都配有由 AE 提供的潜载体。 这种本地化的表示方式可以使生成过程更加清晰( 因为以细胞为基础的潜载体可以以新的方式结合)以及空间控制(例如通过捆绑框) 。 我们的方法超越了所有既定评估措施的当前状态, 用于定量评估GANs 的基因化能力。 我们显示了这些措施的局限性, 并提议从统计分析中调整一个可靠的标准作为替代办法。