权值编码的神经隐式3D建模的有效性研究
On the Effectiveness of Weight-Encoded Neural Implicit 3D Shapes
摘要：
神经隐式输出一个数字，指示空间中给定的查询点是在内部、外部还是在表面上。许多先前的工作都集中在_latent-encoded_ neural implantation上，其中特定形状的潜在向量编码也作为输入。虽然提供了潜在空间插值，但这是以任何单一形状的重建精度为代价的。针对每个3D形状训练特定的网络，_weight-encoded_ neural implicit可以放弃潜在向量并将重建精度集中在单个形状的细节上。虽然以前被认为是3D扫描任务的中间表示或作为导致潜在编码任务的玩具问题，但权重编码神经隐式尚未被认真对待作为3D形状表示。在本文中，我们建立了权重编码的神经隐式满足第一类3D形状表示的标准。我们介绍了一套技术贡献，以提高重建精度，收敛性和鲁棒性时，学习有符号的距离场引起的多边形网格-事实上的标准表示。作为一个有损压缩，我们的转换优于标准技术的几何处理。与以前的潜在和权重编码的神经隐式相比，我们表现出优越的鲁棒性，可扩展性和性能。
英文摘要：
A neural implicit outputs a number indicating whether the given query point in space is inside, outside, or on a surface. Many prior works have focused on _latent-encoded_ neural implicits, where a latent vector encoding of a specific shape is also fed as input. While affording latent-space interpolation, this comes at the cost of reconstruction accuracy for any _single_ shape. Training a specific network for each 3D shape, a _weight-encoded_ neural implicit may forgo the latent vector and focus reconstruction accuracy on the details of a single shape. While previously considered as an intermediary representation for 3D scanning tasks or as a toy-problem leading up to latent-encoding tasks, weight-encoded neural implicits have not yet been taken seriously as a 3D shape representation. In this paper, we establish that weight-encoded neural implicits meet the criteria of a first-class 3D shape representation. We introduce a suite of technical contributions to improve reconstruction accuracy, convergence, and robustness when learning the signed distance field induced by a polygonal mesh -- the _de facto_ standard representation. Viewed as a lossy compression, our conversion outperforms standard techniques from geometry processing. Compared to previous latent- and weight-encoded neural implicits we demonstrate superior robustness, scalability, and performance.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
