NeRF-Insert: 3D Local Editing with Multimodal Control Signals

arXiv:2404.19204v1 Announce Type: new
Abstract: We propose NeRF-Insert, a NeRF editing framework that allows users to make high-quality local edits with a flexible level of control. Unlike previous work that relied on image-to-image models, we cast scene editing as an in-painting problem, which encourages the global structure of the scene to be preserved. Moreover, while most existing methods use only textual prompts to condition edits, our framework accepts a combination of inputs of different modalities as reference. More precisely, a …

abstract arxiv control cs.ai cs.cv cs.gr editing framework global image image-to-image multimodal nerf painting quality type work