Existing inverse rendering combined with neural rendering methods can only perform editable novel view synthesis on object-specific scenes, while we present intrinsic neural radiance fields, dubbed IntrinsicNeRF, which introduce intrinsic decomposition into the NeRF-based neural rendering method and can extend its application to room-scale scenes. Since intrinsic decomposition is a fundamentally under-constrained inverse problem, we propose a novel distance-aware point sampling and adaptive reflectance iterative clustering optimization method, which enables IntrinsicNeRF with traditional intrinsic decomposition constraints to be trained in an unsupervised manner, resulting in multi-view consistent intrinsic decomposition results. To cope with the problem that different adjacent instances of similar reflectance in a scene are incorrectly clustered together, we further propose a hierarchical clustering method with coarse-to-fine optimization to obtain a fast hierarchical indexing representation. It supports compelling real-time augmented applications such as recoloring and illumination variation. Extensive experiments and editing samples on both object-specific/room-scale scenes and synthetic/real-word data demonstrate that we can obtain consistent intrinsic decomposition results and high-fidelity novel view synthesis even for challenging sequences.

翻译：现有逆渲染与神经渲染结合的方法仅能对物体特定场景进行可编辑的新颖视图合成，而本文提出的本征神经辐射场（IntrinsicNeRF）将本征分解引入基于NeRF的神经渲染方法，并将其应用扩展到房间尺度场景。由于本征分解本质上是一个欠约束的逆问题，本文提出一种新颖的距离感知点采样与自适应反射率迭代聚类优化方法，使IntrinsicNeRF能够在传统本征分解约束下以无监督方式训练，从而获得多视图一致的本征分解结果。针对场景中相似反射率的不同相邻实例被错误聚类的问题，本文进一步提出一种从粗到细优化的层次聚类方法，以快速获得层次化索引表示。该方法支持色彩重映射和光照变化等实时增强现实应用。在物体特定/房间尺度场景以及合成/真实数据上进行的广泛实验和编辑样例表明，即使对于具有挑战性的序列，我们也能获得一致的本征分解结果和高保真新颖视图合成。