DATENeRF: Depth-Aware Text-based Editing of NeRFs

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Rojas, Sara, Philip, Julien, Zhang, Kai, Bi, Sai, Luan, Fujun, Ghanem, Bernard, Sunkavall, Kalyan
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910549940371456
author Rojas, Sara
Philip, Julien
Zhang, Kai
Bi, Sai
Luan, Fujun
Ghanem, Bernard
Sunkavall, Kalyan
author_facet Rojas, Sara
Philip, Julien
Zhang, Kai
Bi, Sai
Luan, Fujun
Ghanem, Bernard
Sunkavall, Kalyan
contents Recent advancements in diffusion models have shown remarkable proficiency in editing 2D images based on text prompts. However, extending these techniques to edit scenes in Neural Radiance Fields (NeRF) is complex, as editing individual 2D frames can result in inconsistencies across multiple views. Our crucial insight is that a NeRF scene's geometry can serve as a bridge to integrate these 2D edits. Utilizing this geometry, we employ a depth-conditioned ControlNet to enhance the coherence of each 2D image modification. Moreover, we introduce an inpainting approach that leverages the depth information of NeRF scenes to distribute 2D edits across different images, ensuring robustness against errors and resampling challenges. Our results reveal that this methodology achieves more consistent, lifelike, and detailed edits than existing leading methods for text-driven NeRF scene editing.
format Preprint
id arxiv_https___arxiv_org_abs_2404_04526
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DATENeRF: Depth-Aware Text-based Editing of NeRFs
Rojas, Sara
Philip, Julien
Zhang, Kai
Bi, Sai
Luan, Fujun
Ghanem, Bernard
Sunkavall, Kalyan
Computer Vision and Pattern Recognition
Recent advancements in diffusion models have shown remarkable proficiency in editing 2D images based on text prompts. However, extending these techniques to edit scenes in Neural Radiance Fields (NeRF) is complex, as editing individual 2D frames can result in inconsistencies across multiple views. Our crucial insight is that a NeRF scene's geometry can serve as a bridge to integrate these 2D edits. Utilizing this geometry, we employ a depth-conditioned ControlNet to enhance the coherence of each 2D image modification. Moreover, we introduce an inpainting approach that leverages the depth information of NeRF scenes to distribute 2D edits across different images, ensuring robustness against errors and resampling challenges. Our results reveal that this methodology achieves more consistent, lifelike, and detailed edits than existing leading methods for text-driven NeRF scene editing.
title DATENeRF: Depth-Aware Text-based Editing of NeRFs
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.04526