We advocate the use of implicit fields for learning generative models of shapes and introduce an implicit field decoder for shape generation, aimed at improving the visual quality of the generated shapes. An implicit field assigns a value to each point in 3D space, so that a shape can be extracted as an iso-surface. Our implicit field decoder is trained to perform this assignment by means of a binary classifier. Specifically, it takes a point coordinate, along with a feature vector encoding a shape, and outputs a value which indicates whether the point is outside the shape or not. By replacing conventional decoders by our decoder for representation learning and generative modeling of shapes, we demonstrate superior results for tasks such as shape autoencoding, generation, interpolation, and single-view 3D reconstruction, particularly in terms of visual quality.
翻译:我们主张使用隐含字段来学习形状的基因模型,并为形状生成引入一个隐含的字段解码器,目的是提高生成形状的视觉质量。一个隐含字段为3D空间的每个点指定了值,以便能够将形状作为异表提取。我们隐含的字段解码器受过培训,能够通过二元分类器完成这一任务。具体地说,它需要一个点坐标,加上一个特性矢量编码一个形状,并输出一个值,表明该点是否在形状之外。我们用我们的解码器替换传统的解码器,用于代表学习和形状的基因建模,我们通过对形状自动编码、生成、内插和单视3D重建等任务展示优异的结果,特别是在视觉质量方面。