StructuredField:统一结构化几何与辐射场
StructuredField: Unifying Structured Geometry and Radiance Field
AI总结:
提出 StructuredField 表示法,利用结构化四面体网格重新参数化为 3D Gaussian 原语实现高保真可微渲染,结合分层隐式细分和无翻转同胚约束,生成无翻转且共形的高质量网格,重建效果媲美 3DGS 并支持物理仿真等应用。
摘要:
近期基于点的可微渲染技术在保真度重建和快速渲染方面取得了显著成功。然而,由于基于点的表示具有非结构化特性,它们难以应用于为结构化网格设计的现代图形管线,也难以适用于与结构化网格表示配合良好的各种仿真和编辑算法。为此,我们提出了 StructuredField,这是一种新颖的表示方法,能够同时实现重建对象的结构化几何表示和高保真渲染重建。我们采用结构化四面体网格来表示重建对象。我们将这些四面体的几何属性重新参数化为 3D Gaussian 原语的参数,从而直接从网格实现可微的高保真渲染。此外,采用分层隐式细分策略以确保网格的共形结构,同时赋予该表示捕捉多尺度细节的能力。为了在优化过程中保持几何完整性,我们提出了一种新颖的无翻转同胚约束来限制四面体网格,保证其在优化过程和最终结果中均无翻转且无自相交。基于我们提出的 StructuredField,我们获得了完全无翻转且共形的高质量结构化网格,同时取得了与 3DGS 相当的重建结果。我们还展示了该表示在物理仿真、变形和细节层次等各种应用中的适用性。
英文摘要:
Recent point-based differentiable rendering techniques have achieved significant success in high-fidelity reconstruction and fast rendering. However, due to the unstructured nature of point-based representations, they are difficult to apply to modern graphics pipelines designed for structured meshes, as well as to a variety of simulation and editing algorithms that work well with structured mesh representations. To this end, we propose StructuredField, a novel representation that achieves both a structured geometric representation of the reconstructed object and high-fidelity rendering reconstruction. We employ structured tetrahedral meshes to represent the reconstructed object. We reparameterize the geometric attributes of these tetrahedra into the parameters of 3D Gaussian primitives, thereby enabling differentiable, high-fidelity rendering directly from the mesh. Furthermore, a hierarchical implicit subdivision strategy is utilized to ensure a conformal mesh structure while empowering the representation to capture multi-scale details. To maintain geometric integrity during optimization, we propose a novel inversion-free homeomorphism that constrains the tetrahedral mesh, guaranteeing it remains both inversion-free and self-intersection-free during the optimization process and in the final result. Based on our proposed StructuredField, we achieve high-quality structured meshes that are completely inversion-free and conformal, while also attaining reconstruction results comparable to those of 3DGS. We also demonstrate the applicability of our representation to various applications such as physical simulation, deformation, and level-of-detail.
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。