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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sabat, Benet Oriol, Achille, Alessandro, Trager, Matthew, Soatto, Stefano
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917654126657536
author Sabat, Benet Oriol
Achille, Alessandro
Trager, Matthew
Soatto, Stefano
author_facet Sabat, Benet Oriol
Achille, Alessandro
Trager, Matthew
Soatto, Stefano
contents 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 user may provide a combination of textual and visual inputs including images, CAD models, and binary image masks for specifying a 3D region. We use generic image generation models to in-paint the scene from multiple viewpoints, and lift the local edits to a 3D-consistent NeRF edit. Compared to previous methods, our results show better visual quality and also maintain stronger consistency with the original NeRF.
format Preprint
id arxiv_https___arxiv_org_abs_2404_19204
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle NeRF-Insert: 3D Local Editing with Multimodal Control Signals
Sabat, Benet Oriol
Achille, Alessandro
Trager, Matthew
Soatto, Stefano
Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
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 user may provide a combination of textual and visual inputs including images, CAD models, and binary image masks for specifying a 3D region. We use generic image generation models to in-paint the scene from multiple viewpoints, and lift the local edits to a 3D-consistent NeRF edit. Compared to previous methods, our results show better visual quality and also maintain stronger consistency with the original NeRF.
title NeRF-Insert: 3D Local Editing with Multimodal Control Signals
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Graphics
url https://arxiv.org/abs/2404.19204