让机器人用语言操控3D场景，一次建模多次编辑。
NEO: NeRF It Once, Edit It Many Times for Continuous Object Manipulation
- 结合多视角一致渐进修复与神经场重采样实现语言引导删物
- 通过师生模型直接编辑NeRF权重，预演动作后场景状态
- 首个专为机器人操作设计的NeRF编辑评测集，可量化对比
本文提出NEO，一种统一框架，支持语言引导的神经辐射场（NeRF）编辑以实现连续物体操作。该方法包含：(i) 结合神经场重采样与多视图一致渐进修复的语言引导物体移除；(ii) 基于知识蒸馏的直接NeRF权重编辑方法，通过教师-学生模型融合原始与编辑后的NeRF，实现动作前未来场景状态的一致建模；(iii) 首个适用于机器人操作的NeRF场景编辑评测基准（NEO-Dataset）。实验表明，本方法在物体移除和抓取放置任务中均优于现有最先进基线，生成结果视觉连贯、几何一致，显著减少以往方法引入的伪影。
原文摘要 · Abstract (English)
In this paper, we present NEO, a unified framework providing language-guided NeRF editing for robotic manipulation. Our paper introduces (i) a language-guided object removal that combines neural field resampling with multiview-consistent progressive inpainting, (ii) a direct NeRF weight editing method utilizing knowledge distillation, composing original and edited NeRFs via a teacher-student model, enabling coherent modeling of future scene states before a robot executes an action, and (iii) the first benchmark (NEO-Dataset) for quantitatively evaluating NeRF scene editing methods suitable for robot manipulation. We show that our approach outperforms state-of-the-art baselines in scene editing tasks, including object removal and pick-and-place robotic experiments, yielding visually coherent and geometrically consistent edits that reduce artifacts commonly introduced by prior methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。