GaussianEditor：使用文本指令精细编辑 3D 高斯
GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions
AI总结：
针对 3D 场景局部精细编辑的挑战，提出 GaussianEditor 框架，通过提取文本指令对应的感兴趣区域并映射至 3D 高斯以控制编辑过程，实现了比以往更精细准确的 3D 场景编辑，且训练速度提升两倍以上。
摘要：
最近，基于 2D 扩散模型的文本指令在 3D 场景编辑中取得了令人瞩目的成果。然而，当前的扩散模型主要通过在潜空间中预测噪声来生成图像，且编辑通常应用于整张图像，这使得对 3D 场景进行精细（尤其是局部化）编辑具有挑战性。受近期 3D Gaussian splatting 的启发，我们提出了一个系统性框架，命名为 GaussianEditor，通过 3D 高斯并借助文本指令来精细编辑 3D 场景。得益于 3D 高斯的显式特性，我们设计了一系列技术以实现精细编辑。具体而言，我们首先提取与文本指令对应的感兴趣区域（RoI），并将其与 3D 高斯对齐。该高斯 RoI 进一步用于控制编辑过程。我们的框架能够比以往方法实现更精细、更精确的 3D 场景编辑，同时享有更快的训练速度，即在单张 V100 GPU 上不超过 20 分钟，比 Instruct-NeRF2NeRF（45 分钟至 2 小时）快两倍以上。
英文摘要：
Recently, impressive results have been achieved in 3D scene editing with text instructions based on a 2D diffusion model. However, current diffusion models primarily generate images by predicting noise in the latent space, and the editing is usually applied to the whole image, which makes it challenging to perform delicate, especially localized, editing for 3D scenes. Inspired by recent 3D Gaussian splatting, we propose a systematic framework, named GaussianEditor, to edit 3D scenes delicately via 3D Gaussians with text instructions. Benefiting from the explicit property of 3D Gaussians, we design a series of techniques to achieve delicate editing. Specifically, we first extract the region of interest (RoI) corresponding to the text instruction, aligning it to 3D Gaussians. The Gaussian RoI is further used to control the editing process. Our framework can achieve more delicate and precise editing of 3D scenes than previous methods while enjoying much faster training speed, i.e. within 20 minutes on a single V100 GPU, more than twice as fast as Instruct-NeRF2NeRF (45 minutes -- 2 hours).
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。
