In recent years, implicit surface representations through neural networks that encode the signed distance have gained popularity and have achieved state-of-the-art results in various tasks (e.g. shape representation, shape reconstruction, and learning shape priors). However, in contrast to conventional shape representations such as polygon meshes, the implicit representations cannot be easily edited and existing works that attempt to address this problem are extremely limited. In this work, we propose the first method for efficient interactive editing of signed distance functions expressed through neural networks, allowing free-form editing. Inspired by 3D sculpting software for meshes, we use a brush-based framework that is intuitive and can in the future be used by sculptors and digital artists. In order to localize the desired surface deformations, we regulate the network by using a copy of it to sample the previously expressed surface. We introduce a novel framework for simulating sculpting-style surface edits, in conjunction with interactive surface sampling and efficient adaptation of network weights. We qualitatively and quantitatively evaluate our method in various different 3D objects and under many different edits. The reported results clearly show that our method yields high accuracy, in terms of achieving the desired edits, while at the same time preserving the geometry outside the interaction areas.
翻译:近些年来,通过神经网络对经签署的距离进行编码的隐含表面表层表达方式,在各种任务(如形状代表、形状重建、和学习形状前期)中获得了最先进的成果。然而,与传统的形状表现方式,如多边形网外观相比,隐含表面表示方式不容易编辑,试图解决这一问题的现有工作极为有限。在这项工作中,我们提出了通过神经网络对经签署的远距离功能进行高效互动编辑的第一个方法,允许自由形式编辑。在3D模具雕塑软件的启发下,我们使用一个基于刷子的框架,这种框架是直观的,将来可以由雕塑家和数字艺术家使用。为了将理想表面变形方式本地化,我们用它的副本来对网络进行规范。我们提出了一个新的框架,用以模拟雕塑式表面编辑方式的编辑方式,同时允许自由形式编辑。我们从质量和数量上评估了我们的方法,在不同3D对象和不同地理目标下,在很多不同时间的修改下,在高精确度上实现了我们所期望的精确度。所报告的结果清楚地表明,在外部的精确度上保持了我们所使用的方法。