We propose InNeRF360, an automatic system that accurately removes text-specified objects from 360-degree Neural Radiance Fields (NeRF). The challenge is to effectively remove objects while inpainting perceptually consistent content for the missing regions, which is particularly demanding for existing NeRF models due to their implicit volumetric representation. Moreover, unbounded scenes are more prone to floater artifacts in the inpainted region than frontal-facing scenes, as the change of object appearance and background across views is more sensitive to inaccurate segmentations and inconsistent inpainting. With a trained NeRF and a text description, our method efficiently removes specified objects and inpaints visually consistent content without artifacts. We apply depth-space warping to enforce consistency across multiview text-encoded segmentations, and then refine the inpainted NeRF model using perceptual priors and 3D diffusion-based geometric priors to ensure visual plausibility. Through extensive experiments in segmentation and inpainting on 360-degree and frontal-facing NeRFs, we show that our approach is effective and enhances NeRF's editability. Project page: https://ivrl.github.io/InNeRF360.

翻译：我们提出了InNeRF360，一种能够从360度神经辐射场（NeRF）中精确移除文本指定对象的自动化系统。其挑战在于有效移除对象的同时，对缺失区域进行感知一致的内容修复，这对现有NeRF模型因隐式体积表示而言尤为困难。此外，无界场景比正面场景更容易在修复区域产生浮动伪影，因为对象外观和背景随视角的变化对不精确分割与不一致修复更为敏感。基于已训练的NeRF模型和文本描述，我们的方法能够高效移除指定对象，并修复视觉一致且无伪影的内容。我们采用深度空间变形来强制多视角文本编码分割的一致性，然后利用感知先验和基于3D扩散的几何先验优化修复后的NeRF模型，确保视觉合理性。通过在360度及正面场景NeRF上的分割与修复大量实验，我们证明了该方法的有效性，并增强了NeRF的可编辑性。项目页面：https://ivrl.github.io/InNeRF360。