InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Bao, Yanqi, Ding, Tianyu, Huo, Jing, Li, Wenbin, Li, Yuxin, Gao, Yang
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914725473812480
author Bao, Yanqi
Ding, Tianyu
Huo, Jing
Li, Wenbin
Li, Yuxin
Gao, Yang
author_facet Bao, Yanqi
Ding, Tianyu
Huo, Jing
Li, Wenbin
Li, Yuxin
Gao, Yang
contents Generalizing Neural Radiance Fields (NeRF) to new scenes is a significant challenge that existing approaches struggle to address without extensive modifications to vanilla NeRF framework. We introduce InsertNeRF, a method for INStilling gEneRalizabiliTy into NeRF. By utilizing multiple plug-and-play HyperNet modules, InsertNeRF dynamically tailors NeRF's weights to specific reference scenes, transforming multi-scale sampling-aware features into scene-specific representations. This novel design allows for more accurate and efficient representations of complex appearances and geometries. Experiments show that this method not only achieves superior generalization performance but also provides a flexible pathway for integration with other NeRF-like systems, even in sparse input settings. Code will be available https://github.com/bbbbby-99/InsertNeRF.
format Preprint
id arxiv_https___arxiv_org_abs_2308_13897
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules
Bao, Yanqi
Ding, Tianyu
Huo, Jing
Li, Wenbin
Li, Yuxin
Gao, Yang
Computer Vision and Pattern Recognition
Generalizing Neural Radiance Fields (NeRF) to new scenes is a significant challenge that existing approaches struggle to address without extensive modifications to vanilla NeRF framework. We introduce InsertNeRF, a method for INStilling gEneRalizabiliTy into NeRF. By utilizing multiple plug-and-play HyperNet modules, InsertNeRF dynamically tailors NeRF's weights to specific reference scenes, transforming multi-scale sampling-aware features into scene-specific representations. This novel design allows for more accurate and efficient representations of complex appearances and geometries. Experiments show that this method not only achieves superior generalization performance but also provides a flexible pathway for integration with other NeRF-like systems, even in sparse input settings. Code will be available https://github.com/bbbbby-99/InsertNeRF.
title InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2308.13897