This paper addresses the challenge of Neural Field (NeF) generalization, where models must efficiently adapt to new signals given only a few observations. To tackle this, we propose Geometric Neural Process Fields (G-NPF), a probabilistic framework for neural radiance fields that explicitly captures uncertainty. We formulate NeF generalization as a probabilistic problem, enabling direct inference of NeF function distributions from limited context observations. To incorporate structural inductive biases, we introduce a set of geometric bases that encode spatial structure and facilitate the inference of NeF function distributions. Building on these bases, we design a hierarchical latent variable model, allowing G-NPF to integrate structural information across multiple spatial levels and effectively parameterize INR functions. This hierarchical approach improves generalization to novel scenes and unseen signals. Experiments on novel-view synthesis for 3D scenes, as well as 2D image and 1D signal regression, demonstrate the effectiveness of our method in capturing uncertainty and leveraging structural information for improved generalization.
View on arXiv@article{yin2025_2502.02338,
title={ Geometric Neural Process Fields },
author={ Wenzhe Yin and Zehao Xiao and Jiayi Shen and Yunlu Chen and Cees G. M. Snoek and Jan-Jakob Sonke and Efstratios Gavves },
journal={arXiv preprint arXiv:2502.02338},
year={ 2025 }
}