In this paper, we present Gaussian Splatting based text-to-3D generation (GSGEN), a novel approach for generating high-quality 3D objects. Previous methods suffer from inaccurate geometry and limited fidelity due to the absence of 3D prior and proper representation. We leverage 3D Gaussian Splatting, a recent state-of-the-art representation, to address existing shortcomings by exploiting the explicit nature that enables the incorporation of 3D prior. Specifically, our method adopts a progressive optimization strategy, which includes a geometry optimization stage and an appearance refinement stage. In geometry optimization, a coarse representation is established under a 3D geometry prior along with the ordinary 2D SDS loss, ensuring a sensible and 3D-consistent rough shape. Subsequently, the obtained Gaussians undergo an iterative refinement to enrich details. In this stage, we increase the number of Gaussians by compactness-based densification to enhance continuity and improve fidelity. With these designs, our approach can generate 3D content with delicate details and more accurate geometry. Extensive evaluations demonstrate the effectiveness of our method, especially for capturing high-frequency components. Video results are provided at https://gsgen3d.github.io. Our code is available at https://github.com/gsgen3d/gsgen

翻译：本文提出基于高斯泼溅的文本到3D生成方法（GSGEN），一种生成高质量3D物体的新方法。由于缺乏3D先验和合适的表示，先前方法存在几何不准确和保真度有限的问题。我们利用近期最先进的3D高斯泼溅表示法，通过其显式特性引入3D先验，从而解决现有缺陷。具体而言，我们的方法采用渐进式优化策略，包含几何优化和外观精化两个阶段。在几何优化阶段，结合3D几何先验与常规2D SDS损失建立粗略表示，确保生成合理且具有3D一致性的粗糙形状。随后，对所得高斯体进行迭代精化以丰富细节。在该阶段，我们通过基于紧凑性的稠密化增加高斯体数量，以增强连续性和提升保真度。通过这些设计，我们的方法能够生成具有精细细节和更准确几何的3D内容。大量评估证明了我们方法的有效性，尤其在捕捉高频分量方面。视频结果见https://gsgen3d.github.io，代码见https://github.com/gsgen3d/gsgen