RePaint-NeRF：通过语义掩码和扩散模型进行 NeRF 编辑
RePaint-NeRF: NeRF Editting via Semantic Masks and Diffusion Models
AI总结：
提出 RePaint-NeRF 框架，结合语义掩码与预训练扩散模型引导 NeRF 生成指定三维对象，并在真实与合成数据集上验证其外观和形状编辑效果。
摘要：
神经辐射场（Neural Radiance Fields，NeRF）的出现推动了对复杂真实世界的高保真视图合成的发展。然而，重绘 NeRF 中的内容仍然是一项要求很高的任务。本文提出了一种新颖框架，能够以 RGB 图像作为输入，并改变神经场景中的三维内容。我们的工作利用现有扩散模型来指导指定三维内容的变化。具体而言，我们通过语义方式选择目标对象，预训练扩散模型将引导 NeRF 模型生成新的三维对象，从而提升 NeRF 的可编辑性、多样性和应用范围。实验结果表明，在不同文本提示下，我们的算法能够有效编辑 NeRF 中的三维对象，包括编辑外观、形状等。针对这些编辑任务，我们在真实世界数据集和合成世界数据集上均验证了该方法。如需更好地查看结果，请访问 https://starstesla.github.io/repaintnerf。
英文摘要：
The emergence of Neural Radiance Fields (NeRF) has promoted the development of synthesized high-fidelity views of the intricate real world. However, it is still a very demanding task to repaint the content in NeRF. In this paper, we propose a novel framework that can take RGB images as input and alter the 3D content in neural scenes. Our work leverages existing diffusion models to guide changes in the designated 3D content. Specifically, we semantically select the target object and a pre-trained diffusion model will guide the NeRF model to generate new 3D objects, which can improve the editability, diversity, and application range of NeRF. Experiment results show that our algorithm is effective for editing 3D objects in NeRF under different text prompts, including editing appearance, shape, and more. We validate our method on both real-world datasets and synthetic-world datasets for these editing tasks. Please visit https://starstesla.github.io/repaintnerf for a better view of our results.
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。
