NeuGen: Amplifying the 'Neural' in Neural Radiance Fields for Domain Generalization

TL;DR

NeuGen introduces a brain-inspired normalization technique to improve the generalization and robustness of Neural Radiance Fields across diverse scenes, surpassing existing models in accuracy and rendering quality.

Contribution

The paper presents NeuGen, a novel normalization method inspired by neuroscience, integrated into NeRF architectures to enhance their domain generalization capabilities.

Findings

NeuGen improves NeRF performance on multiple benchmarks.

Enhanced generalization across diverse datasets.

Significant gains in rendering quality and robustness.

Abstract

Neural Radiance Fields (NeRF) have significantly advanced the field of novel view synthesis, yet their generalization across diverse scenes and conditions remains challenging. Addressing this, we propose the integration of a novel brain-inspired normalization technique Neural Generalization (NeuGen) into leading NeRF architectures which include MVSNeRF and GeoNeRF. NeuGen extracts the domain-invariant features, thereby enhancing the models' generalization capabilities. It can be seamlessly integrated into NeRF architectures and cultivates a comprehensive feature set that significantly improves accuracy and robustness in image rendering. Through this integration, NeuGen shows improved performance on benchmarks on diverse datasets across state-of-the-art NeRF architectures, enabling them to generalize better across varied scenes. Our comprehensive evaluations, both quantitative and qualitative, confirm that our approach not only surpasses existing models in generalizability but also markedly improves rendering quality. Our work exemplifies the potential of merging neuroscientific principles with deep learning frameworks, setting a new precedent for enhanced generalizability and efficiency in novel view synthesis. A demo of our study is available at https://neugennerf.github.io.