IntrinsicNeRF：学习内在神经辐射场以实现可编辑的新视角合成
IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis
AI总结：
IntrinsicNeRF将内在分解引入NeRF，通过距离感知采样和自适应反射率迭代聚类实现无监督训练，支持房间级场景的实时重着色与光照编辑，并保持高保真新视角合成。
摘要：
现有的将逆渲染与神经渲染相结合的方法只能在特定物体的场景上进行可编辑的新视角合成，而我们提出了内在神经辐射场（IntrinsicNeRF），它将内在分解引入基于NeRF的神经渲染方法中，并能够将其应用扩展到房间规模的场景。由于内在分解本质上是一个约束不足的逆问题，我们提出了一种新颖的基于距离感知的点采样和自适应反射率迭代聚类优化方法，这使得IntrinsicNeRF能够在传统内在分解约束下以无监督方式进行训练，从而获得多视角一致的内在分解结果。为了解决场景中具有相似反射率的相邻不同实例被错误地聚类在一起的问题，我们进一步提出了一种从粗到细优化的层次聚类方法，以获得快速的层次索引表示。它支持令人信服的实时增强应用，如重新着色和光照变化。在物体特定/房间规模场景以及合成/真实世界数据上进行的大量实验和编辑示例表明，即使对于具有挑战性的序列，我们也能获得一致的内在分解结果和高保真的新视角合成。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
