DATENeRF：基于深度感知的文本驱动 NeRF 编辑
DATENeRF: Depth-Aware Text-based Editing of NeRFs
AI总结：
本文提出 DATENeRF，利用 NeRF 场景几何作为桥梁，结合深度条件 ControlNet 和基于深度信息的修复方法，实现更一致、逼真且细致的文本驱动三维场景编辑。
摘要：
近年来，扩散模型在基于文本提示编辑二维图像方面展现出卓越能力。然而，将这些技术扩展到神经辐射场（NeRF）场景的编辑十分复杂，因为编辑单个二维帧可能导致多个视角之间的不一致。我们的关键洞察是：NeRF 场景的几何结构可以作为整合这些二维编辑的桥梁。利用该几何结构，我们采用深度条件化的 ControlNet 来增强每个二维图像修改的连贯性。此外，我们引入一种利用 NeRF 场景深度信息将二维编辑分布到不同图像上的修复方法，确保对错误和重采样挑战具有鲁棒性。实验结果表明，与现有领先的文本驱动 NeRF 场景编辑方法相比，本方法能够实现更一致、更逼真且更精细的编辑效果。
英文摘要：
Recent advancements in diffusion models have shown remarkable proficiency in editing 2D images based on text prompts. However, extending these techniques to edit scenes in Neural Radiance Fields (NeRF) is complex, as editing individual 2D frames can result in inconsistencies across multiple views. Our crucial insight is that a NeRF scene's geometry can serve as a bridge to integrate these 2D edits. Utilizing this geometry, we employ a depth-conditioned ControlNet to enhance the coherence of each 2D image modification. Moreover, we introduce an inpainting approach that leverages the depth information of NeRF scenes to distribute 2D edits across different images, ensuring robustness against errors and resampling challenges. Our results reveal that this methodology achieves more consistent, lifelike, and detailed edits than existing leading methods for text-driven NeRF scene 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。
