InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules
Yanqi Bao, Tianyu Ding, Jing Huo, Wenbin Li, Yuxin Li, Yang Gao
Abstract
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 **INS**tilling g**E**ne**R**alizabili**T**y 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 at: https://github.com/bbbbby-99/InsertNeRF.
BibTeX
@inproceedings{
bao2024insertnerf,
title={InsertNe{RF}: Instilling Generalizability into Ne{RF} with HyperNet Modules},
author={Yanqi Bao and Tianyu Ding and Jing Huo and Wenbin Li and Yuxin Li and Yang Gao},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=aHmNpLlUlb}
}