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

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 domain-invariant features, thereby enhancing the models' generalization capabilities. Our methodology involves fine-tuning pre-trained NeRF models with the incorporation of NeuGen, which facilitates the construction of a more informative feature set that leads to an accurate and robust rendering of images. Through this integration, NeuGen shows benchmarking performance 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.