定制你的NeRF：通过局部-全局迭代训练实现自适应源驱动的3D场景编辑
Customize your NeRF: Adaptive Source Driven 3D Scene Editing via Local-Global Iterative Training
AI总结：
本文提出CustomNeRF模型，通过局部-全局迭代训练和类别引导正则化，解决文本或图像驱动的3D场景编辑中前景精确编辑与多视角一致性问题。
摘要：
本文针对自适应源驱动的3D场景编辑任务，提出了一种CustomNeRF模型，该模型将文本描述或参考图像统一作为编辑提示。然而，获得符合编辑提示的期望编辑结果并非易事，因为存在两个重大挑战：仅对前景区域进行精确编辑，以及在给定单视角参考图像的情况下保持多视角一致性。为应对第一个挑战，我们提出了一种局部-全局迭代编辑（LGIE）训练方案，该方案在前景区域编辑和全图编辑之间交替进行，旨在仅操作前景的同时保留背景。针对第二个挑战，我们还设计了一种类别引导正则化方法，利用生成模型中的类别先验来缓解图像驱动编辑中不同视角之间的不一致问题。大量实验表明，我们的CustomNeRF在文本驱动和图像驱动设置下，均能在各种真实场景中产生精确的编辑结果。
英文摘要：
In this paper, we target the adaptive source driven 3D scene editing task by proposing a CustomNeRF model that unifies a text description or a reference image as the editing prompt. However, obtaining desired editing results conformed with the editing prompt is nontrivial since there exist two significant challenges, including accurate editing of only foreground regions and multi-view consistency given a single-view reference image. To tackle the first challenge, we propose a Local-Global Iterative Editing (LGIE) training scheme that alternates between foreground region editing and full-image editing, aimed at foreground-only manipulation while preserving the background. For the second challenge, we also design a class-guided regularization that exploits class priors within the generation model to alleviate the inconsistency problem among different views in image-driven editing. Extensive experiments show that our CustomNeRF produces precise editing results under various real scenes for both text- and image-driven settings.
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。
