NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFs
This enables mix-and-match exploration of 3D geometry and appearance for 3D scene editing applications.
The paper tackles the problem of transferring appearance from one Neural Radiance Field (NeRF) to another while preserving target geometry in a semantically meaningful way, achieving multi-view consistent results that outperform traditional stylization methods and are preferred by a large majority of users.
A Neural Radiance Field (NeRF) encodes the specific relation of 3D geometry and appearance of a scene. We here ask the question whether we can transfer the appearance from a source NeRF onto a target 3D geometry in a semantically meaningful way, such that the resulting new NeRF retains the target geometry but has an appearance that is an analogy to the source NeRF. To this end, we generalize classic image analogies from 2D images to NeRFs. We leverage correspondence transfer along semantic affinity that is driven by semantic features from large, pre-trained 2D image models to achieve multi-view consistent appearance transfer. Our method allows exploring the mix-and-match product space of 3D geometry and appearance. We show that our method outperforms traditional stylization-based methods and that a large majority of users prefer our method over several typical baselines.