OR-NeRF：基于神经辐射场、由多视图分割引导的3D场景物体移除
OR-NeRF: Object Removing from 3D Scenes Guided by Multiview Segmentation with Neural Radiance Fields
AI总结：
本文提出OR-NeRF，利用单视图点或文本提示，结合3D几何传播、SAM分割、2D修复及深度与感知监督，高效实现一致的3D场景物体移除。
摘要：
用于新视图合成的神经辐射场（Neural Radiance Fields，NeRF）的出现，提升了人们对3D场景编辑的兴趣。编辑中的一项关键任务是在保证视觉合理性和多视图一致性的同时从场景中移除物体。然而，当前方法面临诸多挑战，例如物体标注耗时、移除特定目标的能力有限，以及移除后渲染质量受损。本文提出了一种名为OR-NeRF的新型物体移除流程，它能够利用用户在单个视图上给出的点或文本提示从3D场景中移除物体，并以比以往工作更少的时间取得更优性能。我们的方法通过3D几何和稀疏对应关系将用户标注传播到所有视图，以较小的处理负担确保3D一致性。随后，采用近期的2D分割模型Segment-Anything（SAM）预测掩码，并使用2D修复模型生成颜色监督。最后，我们的算法施加深度监督和感知损失，以在物体移除后保持几何与外观的一致性。实验结果表明，在定性和定量两方面加以考虑时，我们的方法都能以比以往工作更少的时间实现更优的编辑质量。
英文摘要：
The emergence of Neural Radiance Fields (NeRF) for novel view synthesis has increased interest in 3D scene editing. An essential task in editing is removing objects from a scene while ensuring visual reasonability and multiview consistency. However, current methods face challenges such as time-consuming object labeling, limited capability to remove specific targets, and compromised rendering quality after removal. This paper proposes a novel object-removing pipeline, named OR-NeRF, that can remove objects from 3D scenes with user-given points or text prompts on a single view, achieving better performance in less time than previous works. Our method spreads user annotations to all views through 3D geometry and sparse correspondence, ensuring 3D consistency with less processing burden. Then recent 2D segmentation model Segment-Anything (SAM) is applied to predict masks, and a 2D inpainting model is used to generate color supervision. Finally, our algorithm applies depth supervision and perceptual loss to maintain consistency in geometry and appearance after object removal. Experimental results demonstrate that our method achieves better editing quality with less time than previous works, considering both quality and quantity.
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。
