NEO: NeRF It Once, Edit It Many Times for Continuous Object Manipulation
TL;DR
This letter introduces a language-guided object removal that combines neural field resampling with multiview-consistent progressive inpainting, a direct NeRF weight editing method utilizing knowledge distillation, and the first benchmark (NEO-Dataset) for quantitatively evaluating NeRF scene editing methods suitable for robot manipulation.
Abstract
In this letter, we present NEO, a unified framework providing language-guided NeRF editing for robotic manipulation. Our letter 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. Finally, we showcase the capability of NEO for multi-stage robotic assembly tasks by preserving a persistent NeRF plus language-field representation after each edit, enabling iterative future-state scene representation prediction without requiring additional scene re-scanning.