EditCast3D：单帧引导的三维编辑，结合视频传播与视角选择
EditCast3D: Single-Frame-Guided 3D Editing with Video Propagation and View Selection
AI总结：
EditCast3D提出利用视频生成模型从单帧传播编辑至整个数据集，并通过视角选择策略确保一致性，实现高效高质量的三维编辑，减少对昂贵图像编辑的依赖。
摘要：
基础模型的最新进展推动了图像编辑领域的显著进步，然而其在三维编辑中的扩展仍未得到充分探索。一种自然的方法是将现有工作流程中的图像编辑模块替换为基础模型。然而，这些模型巨大的计算需求以及闭源API的限制和成本，使得将这些模型插入现有的迭代编辑策略变得不切实际。为解决这一局限，我们提出了EditCast3D，一种利用视频生成基础模型，在重建之前将编辑从单个首帧传播到整个数据集的流程。尽管编辑传播能够通过视频模型实现数据集级别的编辑，但其一致性对于三维重建（其中多视角对齐至关重要）而言仍非最优。为克服这一点，EditCast3D引入了一种视角选择策略，该策略明确识别一致且利于重建的视角，并采用前馈重建，无需昂贵的细化过程。综合来看，该流程既最小化了对昂贵图像编辑的依赖，又缓解了跨图像独立应用基础模型时出现的提示歧义。我们在常用的三维编辑数据集上评估了EditCast3D，并与最先进的三维编辑基线进行了比较，展示了优越的编辑质量和高效率。这些结果确立了EditCast3D作为一种可扩展且通用的范式，用于将基础模型集成到三维编辑流程中。代码可在https://github.com/UNITES-Lab/EditCast3D获取。
英文摘要：
Recent advances in foundation models have driven remarkable progress in image editing, yet their extension to 3D editing remains underexplored. A natural approach is to replace the image editing modules in existing workflows with foundation models. However, their heavy computational demands and the restrictions and costs of closed-source APIs make plugging these models into existing iterative editing strategies impractical. To address this limitation, we propose EditCast3D, a pipeline that employs video generation foundation models to propagate edits from a single first frame across the entire dataset prior to reconstruction. While editing propagation enables dataset-level editing via video models, its consistency remains suboptimal for 3D reconstruction, where multi-view alignment is essential. To overcome this, EditCast3D introduces a view selection strategy that explicitly identifies consistent and reconstruction-friendly views and adopts feedforward reconstruction without requiring costly refinement. In combination, the pipeline both minimizes reliance on expensive image editing and mitigates prompt ambiguities that arise when applying foundation models independently across images. We evaluate EditCast3D on commonly used 3D editing datasets and compare it against state-of-the-art 3D editing baselines, demonstrating superior editing quality and high efficiency. These results establish EditCast3D as a scalable and general paradigm for integrating foundation models into 3D editing pipelines. The code is available at https://github.com/UNITES-Lab/EditCast3D
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。
