Geometric implicit neural representations for signed distance functions
Luiz Schirmer, Tiago Novello, Vinícius da Silva, Guilherme Schardong, Daniel Perazzo, Hélio Lopes, Nuno Gonçalves, Luiz Velho
隐性神经表示(INRs)已成为在低维空间中表示信号的一个有前途的框架。 本调查回顾了关于表面场景近似签名距离函数(SDF)的专用INR问题的现有文献,使用定向点云或一组图景。 我们指的是神经自付费用SDF,它们在其损失函数中加入了微分几何工具,如正态和曲率,作为几何INR。 这种3D重建方法背后的关键思想是在损失函数中包括额外的正则化术语,确保INR满足该函数应持有的某些全局属性 - 例如在自开发中具有单位梯度。 我们探索关键的方法论组件,包括INR的定义,几何损失函数的构建,以及从微分几何学角度的采样方案。 我们的审查强调了几何INR在定向点云和图景表面重建中取得的重大进步。
Implicit neural representations (INRs) have emerged as a promising framework for representing signals in low-dimensional spaces. This survey reviews the existing literature on the specialized INR problem of approximating signed distance functions (SDFs) for surface scenes, using either oriented point clouds or a set of posed images. We refer to neural SDFs that incorporate differential geometry tools, such as normals and curvatures, in their loss functions as geometric INRs. The key idea behind ...