Year: 2023
Type: preprint
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 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.
Source: arXiv (Cornell University)
Authors: Bao, Yanqi, Ding, Tianyu, Huo, Jing, Li, Wenbin, Li, Yuxin, Gao, Yang
Institutions: Nanjing University, Microsoft (United States)
Language: English
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4386270168