3D editing plays a crucial role in many areas such as gaming and virtual reality. Traditional 3D editing methods, which rely on representations like meshes and point clouds, often fall short in realistically depicting complex scenes. On the other hand, methods based on implicit 3D representations, like Neural Radiance Field (NeRF), render complex scenes effectively but suffer from slow processing speeds and limited control over specific scene areas. In response to these challenges, our paper presents GaussianEditor, an innovative and efficient 3D editing algorithm based on Gaussian Splatting (GS), a novel 3D representation. GaussianEditor enhances precision and control in editing through our proposed Gaussian semantic tracing, which traces the editing target throughout the training process. Additionally, we propose Hierarchical Gaussian splatting (HGS) to achieve stabilized and fine results under stochastic generative guidance from 2D diffusion models. We also develop editing strategies for efficient object removal and integration, a challenging task for existing methods. Our comprehensive experiments demonstrate GaussianEditor's superior control, efficacy, and rapid performance, marking a significant advancement in 3D editing. Project Page: https://buaacyw.github.io/gaussian-editor/

翻译：三维编辑在游戏和虚拟现实等多个领域扮演着关键角色。传统的基于网格和点云等表征的三维编辑方法，在真实感地描绘复杂场景方面往往力有不逮。另一方面，基于隐式三维表征的方法，如神经辐射场（NeRF），虽能有效渲染复杂场景，但处理速度慢且对特定场景区域的控制能力有限。针对这些挑战，本文提出了高斯编辑器（GaussianEditor），一种基于新型三维表征——高斯泼溅（GS）的创新高效三维编辑算法。通过我们提出的高斯语义追踪，高斯编辑器在训练过程中始终追踪编辑目标，从而提升了编辑的精确度与控制力。此外，我们提出了分层高斯泼溅（HGS），以在来自二维扩散模型的随机生成指导下，获得稳定且精细的结果。我们还开发了针对高效物体移除与集成的编辑策略，这对现有方法而言是一项艰巨任务。我们的全面实验表明，高斯编辑器具备卓越的控制力、高效性与快速性能，标志着三维编辑领域的重大进步。项目主页：https://buaacyw.github.io/gaussian-editor/