用类脑归一化提升NeRF跨场景泛化能力
NeuGen: Amplifying the 'Neural' in Neural Radiance Fields for Domain Generalization
- 引入类脑归一化NeuGen提取领域不变特征
- 在多个数据集上显著提升渲染准确率与鲁棒性
- 适合关注跨场景泛化与图像生成的开发者
神经辐射场（NeRF）虽大幅推动了新视角合成发展，但其在不同场景与条件下的泛化能力仍受限。为此，我们提出将新型类脑归一化技术NeuGen集成至主流NeRF架构（包括MVSNeRF和GeoNeRF），以提取领域不变特征，增强模型泛化能力。该方法可无缝嵌入现有架构，构建更全面的特征表示，显著提升图像渲染的准确性和鲁棒性。在多个多样化数据集上的综合评估表明，该方法在状态领先NeRF架构中均实现更优泛化性能，并明显改善渲染质量。定量与定性分析共同验证了本方法在通用性与效率上的优越性，展示了神经科学原理与深度学习框架融合的潜力，为新视角合成开辟新范式。演示地址：https://neugennerf.github.io。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。