Neural radiance fields (NeRF) show great success in novel view synthesis. However, in real-world scenes, recovering high-quality details from the source images is still challenging for the existing NeRF-based approaches, due to the potential imperfect calibration information and scene representation inaccuracy. Even with high-quality training frames, the synthetic novel views produced by NeRF models still suffer from notable rendering artifacts, such as noise, blur, etc. Towards to improve the synthesis quality of NeRF-based approaches, we propose NeRFLiX, a general NeRF-agnostic restorer paradigm by learning a degradation-driven inter-viewpoint mixer. Specially, we design a NeRF-style degradation modeling approach and construct large-scale training data, enabling the possibility of effectively removing NeRF-native rendering artifacts for existing deep neural networks. Moreover, beyond the degradation removal, we propose an inter-viewpoint aggregation framework that is able to fuse highly related high-quality training images, pushing the performance of cutting-edge NeRF models to entirely new levels and producing highly photo-realistic synthetic views.

翻译：神经辐射场（NeRF）在新视图合成领域展现出巨大成功。然而，在真实场景中，由于可能存在不完美的标定信息和场景表示不准确性，现有基于NeRF的方法从源图像恢复高质量细节仍面临挑战。即便使用高质量训练帧，NeRF模型生成的合成新视图仍存在显著的渲染伪影，如噪声、模糊等。为提升基于NeRF方法的合成质量，我们提出NeRFLiX——一种通用的与NeRF无关的修复范式，通过学习退化驱动的视角间混合器实现。具体而言，我们设计了一种NeRF风格的退化建模方法，并构建大规模训练数据，使现有深度神经网络能够有效去除NeRF原生渲染伪影。此外，在去除退化之外，我们提出一种视角间聚合框架，能够融合高度相关的优质训练图像，将先进NeRF模型的性能提升至全新水平，并生成高度逼真的合成视图。