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：本文提出基于高斯喷溅的文本到三维生成方法（GSGEN），一种用于生成高质量三维物体的新方法。现有方法由于缺乏三维先验和合适的表示方式，常存在几何不准确和保真度有限的问题。我们利用最近提出的最先进表示方法——三维高斯喷溅，通过发挥其显式特性来融入三维先验，以解决现有不足。具体而言，我们的方法采用渐进式优化策略，包括几何优化阶段和外观细化阶段。在几何优化阶段，基于三维几何先验并结合常规的二维SDS损失建立粗粒度表示，确保获得合理且三维一致的大致形状。随后，对获得的高斯模型进行迭代细化以丰富细节。在此阶段，我们通过基于紧密性的致密化方法增加高斯数量，以增强连续性并提高保真度。通过上述设计，我们的方法能够生成具有精细细节和更准确几何的三维内容。大量评估证明了本方法的有效性，尤其在捕捉高频分量方面的优势。视频结果见 https://gsgen3d.github.io。我们的代码开源在 https://github.com/gsgen3d/gsgen