DGE：通过一致多视角编辑实现直接高斯3D编辑
DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing
AI总结：
针对开放式语言指令下3D编辑依赖2D引导导致的低效和多视角不一致问题，提出直接高斯编辑器（DGE），通过多视角一致修改2D编辑器并直接优化3D高斯表示，提升编辑效率与准确性，支持局部编辑。
摘要：
我们研究基于开放式语言指令编辑3D对象和场景的问题。该问题的常用方法是利用2D图像生成器或编辑器引导3D编辑过程，从而无需3D数据。但由于需要通过单视角编辑或分数蒸馏采样对神经辐射场等昂贵的3D表示进行迭代更新，此过程通常效率低下。该方法的一大缺点是，由于2D模型的指导不具备多视角一致性，跨视角聚合不一致信息会导致收敛缓慢。为此，我们提出直接高斯编辑器（DGE），分两阶段解决这些问题：首先，通过整合底层场景的3D几何线索，对InstructPix2Pix等高质量图像编辑器进行无训练的多视角一致性修改；其次，基于多视角一致的编辑图像序列，直接高效地优化基于3D高斯溅射的3D表示。由于避免了增量迭代编辑，DGE比现有方法更准确高效，还能实现场景局部选择性编辑。
英文摘要：
We consider the problem of editing 3D objects and scenes based on open-ended language instructions. A common approach to this problem is to use a 2D image generator or editor to guide the 3D editing process, obviating the need for 3D data. However, this process is often inefficient due to the need for iterative updates of costly 3D representations, such as neural radiance fields, either through individual view edits or score distillation sampling. A major disadvantage of this approach is the slow convergence caused by aggregating inconsistent information across views, as the guidance from 2D models is not multi-view consistent. We thus introduce the Direct Gaussian Editor (DGE), a method that addresses these issues in two stages. First, we modify a given high-quality image editor like InstructPix2Pix to be multi-view consistent. To do so, we propose a training-free approach that integrates cues from the 3D geometry of the underlying scene. Second, given a multi-view consistent edited sequence of images, we directly and efficiently optimize the 3D representation, which is based on 3D Gaussian Splatting. Because it avoids incremental and iterative edits, DGE is significantly more accurate and efficient than existing approaches and offers additional benefits, such as enabling selective editing of parts of the scene.
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。
