掌握区域3DGS：利用多样2D先验进行定位、初始化与编辑
Mastering Regional 3DGS: Locating, Initializing, and Editing with Diverse 2D Priors
AI总结：
针对3DGS局部编辑中3D语义解析不足的问题，提出利用2D扩散编辑定位区域、逆渲染定位、2D基础模型深度图初始化粗3DGS，实现迭代视图一致编辑，性能最优且提速4倍。
摘要：
许多3D场景编辑任务侧重于修改局部区域而非整个场景，除了一些全局应用如风格迁移之外。在3D高斯泼溅（3DGS）的背景下，场景由一系列高斯体表示，这种结构允许进行精确的区域编辑，从而增强对场景特定区域的控制；然而，挑战在于3D语义解析的性能往往不如其2D对应方法，这使得在3D空间内进行有针对性的操作更加困难，并限制了编辑的保真度。我们通过利用2D扩散编辑来准确识别每个视图中的修改区域，随后通过逆渲染进行3D定位，然后细化正面视图，并利用由2D基础模型预测的深度图派生出的一致视图和近似形状来初始化一个粗略的3DGS，从而支持一个迭代的、视图一致的编辑过程，逐步增强结构细节和纹理，以确保跨视角的一致性。实验表明，我们的方法在实现最先进性能的同时，提供了高达4倍的加速，为3D场景局部编辑提供了一种更高效且有效的方法。
英文摘要：
Many 3D scene editing tasks focus on modifying local regions rather than the entire scene, except for some global applications like style transfer, and in the context of 3D Gaussian Splatting (3DGS), where scenes are represented by a series of Gaussians, this structure allows for precise regional edits, offering enhanced control over specific areas of the scene; however, the challenge lies in the fact that 3D semantic parsing often underperforms compared to its 2D counterpart, making targeted manipulations within 3D spaces more difficult and limiting the fidelity of edits, which we address by leveraging 2D diffusion editing to accurately identify modification regions in each view, followed by inverse rendering for 3D localization, then refining the frontal view and initializing a coarse 3DGS with consistent views and approximate shapes derived from depth maps predicted by a 2D foundation model, thereby supporting an iterative, view-consistent editing process that gradually enhances structural details and textures to ensure coherence across perspectives. Experiments demonstrate that our method achieves state-of-the-art performance while delivering up to a $4\times$ speedup, providing a more efficient and effective approach to 3D scene local editing.
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。
