Blending-NeRF：神经辐射场中的文本驱动局部编辑
Blending-NeRF: Text-Driven Localized Editing in Neural Radiance Fields
AI总结：
提出Blending-NeRF模型，通过预训练NeRF与可编辑NeRF结合CLIP实现文本驱动的3D对象局部编辑，支持添加、修改和移除操作。
摘要：
3D对象的文本驱动局部编辑尤为困难，因为在不扭曲对象形状的情况下，将原始3D对象与预期的新对象及风格效果进行局部混合并非易事。为解决此问题，我们提出了一种新颖的基于NeRF的模型Blending-NeRF，它由两个NeRF网络组成：预训练NeRF和可编辑NeRF。此外，我们引入了新的混合操作，使Blending-NeRF能够正确编辑由文本定位的目标区域。通过使用预训练的视觉-语言对齐模型CLIP，我们引导Blending-NeRF添加具有不同颜色和密度的新对象、修改纹理，并移除原始对象的部分。大量实验表明，Blending-NeRF能根据各种文本提示生成自然且局部编辑的3D对象。项目页面见https://seokhunchoi.github.io/Blending-NeRF/
英文摘要：
Text-driven localized editing of 3D objects is particularly difficult as locally mixing the original 3D object with the intended new object and style effects without distorting the object's form is not a straightforward process. To address this issue, we propose a novel NeRF-based model, Blending-NeRF, which consists of two NeRF networks: pretrained NeRF and editable NeRF. Additionally, we introduce new blending operations that allow Blending-NeRF to properly edit target regions which are localized by text. By using a pretrained vision-language aligned model, CLIP, we guide Blending-NeRF to add new objects with varying colors and densities, modify textures, and remove parts of the original object. Our extensive experiments demonstrate that Blending-NeRF produces naturally and locally edited 3D objects from various text prompts. Our project page is available at https://seokhunchoi.github.io/Blending-NeRF/
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。
