3D Shape representation has substantial effects on 3D shape reconstruction. Primitive-based representations approximate a 3D shape mainly by a set of simple implicit primitives, but the low geometrical complexity of the primitives limits the shape resolution. Moreover, setting a sufficient number of primitives for an arbitrary shape is challenging. To overcome these issues, we propose a constrained implicit algebraic surface as the primitive with few learnable coefficients and higher geometrical complexities and a deep neural network to produce these primitives. Our experiments demonstrate the superiorities of our method in terms of representation power compared to the state-of-the-art methods in single RGB image 3D shape reconstruction. Furthermore, we show that our method can semantically learn segments of 3D shapes in an unsupervised manner. The code is publicly available from https://myavartanoo.github.io/3dias/ .
翻译:3D 形状表示法对 3D 形状的重建有重大影响。 原始表示法大约3D 形状, 主要是一组简单的隐含原始体, 但原始体的低几何复杂性限制了形状分辨率。 此外, 为任意形状设定足够数量的原始体具有挑战性。 为了克服这些问题, 我们提出一个有限的隐含代数表, 作为原始体, 少有可学系数和较高的几何复杂性, 以及产生这些原始体的深层神经网络。 我们的实验表明,在单一 RGB 图像 3D 形状的重建中,我们的方法在代表力方面优于最先进的方法。 此外, 我们还表明, 我们的方法可以不受监督地以静态学习3D 形状的部块。 该代码可从 https://myavartanoo.github./3dias/ 公开查阅 。