Text-to-3D generation represents an exciting field that has seen rapid advancements, facilitating the transformation of textual descriptions into detailed 3D models. However, current progress often neglects the intricate high-order correlation of geometry and texture within 3D objects, leading to challenges such as over-smoothness, over-saturation and the Janus problem. In this work, we propose a method named “3D Gaussian Generation via Hypergraph (Hyper-3DG)”, designed to capture the sophisticated high-order correlations present within 3D objects. Our framework is anchored by a well-established mainflow and an essential module, named “Geometry and Texture Hypergraph Refiner (HGRefiner)”. This module not only refines the representation of 3D Gaussians but also accelerates the update process of these 3D Gaussians by conducting the Patch-3DGS Hypergraph Learning on both explicit attributes and latent visual features. Our framework allows for the production of finely generated 3D objects within a cohesive optimization, effectively circumventing degradation. Extensive experimentation has shown that our proposed method significantly enhances the quality of 3D generation while incurring no additional computational overhead for the underlying framework. (Project code: https://github.com/yjhboy/Hyper3DG).

文本到 3D 生成是一个令人兴奋的领域，它已经取得了快速发展，促进了文本描述转换为详细的 3D 模型。然而，目前的进展往往忽视了 3D 对象中几何体和纹理的复杂高阶关联，导致了过度平滑、过度饱和和 Janus 问题等挑战。在这项工作中，我们提出了一种名为“通过 Hypergraph 生成 3D 高斯 （Hyper-3DG）”的方法，旨在捕获 3D 对象中存在的复杂高阶相关性。我们的框架由一个完善的主流和一个名为“Geometry and Texture Hypergraph Refiner （HGRefiner）”的基本模块为基础。该模块不仅优化了 3D 高斯的表示，还通过对显式属性和潜在视觉特征执行 Patch-3DGS Hypergraph Learning 来加速这些 3D 高斯的更新过程。我们的框架允许在内聚优化中生成精细生成的 3D 对象，从而有效避免退化。广泛的实验表明，我们提出的方法显著提高了 3D 生成的质量，同时不会为底层框架带来额外的计算开销。（项目代码：https://github.com/yjhboy/Hyper3DG）。