A practical benefit of implicit visual representations like Neural Radiance
Fields (NeRFs) is their memory efficiency: large scenes can be efficiently
stored and shared as small neural nets instead of collections of images.
However, operating on these implicit visual data structures requires extending
classical image-based vision techniques (e.g., registration, blending) from
image sets to neural fields. Towards this goal, we propose NeRFuser, a novel
architecture for NeRF registration and blending that assumes only access to
pre-generated NeRFs, and not the potentially large sets of images used to
generate them. We propose registration from re-rendering, a technique to infer
the transformation between NeRFs based on images synthesized from individual
NeRFs. For blending, we propose sample-based inverse distance weighting to
blend visual information at the ray-sample level. We evaluate NeRFuser on
public benchmarks and a self-collected object-centric indoor dataset, showing
the robustness of our method, including to views that are challenging to render
from the individual source NeRFs.

本文介绍了一种名为 NeRFuser 的架构，它可以在不需要访问大量用于生成它们的图像集的情况下，对 NeRF（神经辐射场）进行注册和混合。NeRFuser 使用 re-rendering 技术进行注册，提出了基于采样的反距离加权进行混合，经实验证明具有鲁棒性。