Skip to yearly menu bar Skip to main content


InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules

Yanqi Bao · Tianyu Ding · Jing Huo · Wenbin Li · Yuxin Li · Yang Gao

Halle B #58
[ ]
Tue 7 May 1:45 a.m. PDT — 3:45 a.m. PDT


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 at:

Chat is not available.