RRM：使用辐射引导材质提取的可重照资产

RRM: Relightable assets using Radiance guided Material extraction

July 8, 2024

作者: Diego Gomez, Julien Philip, Adrien Kaiser, Élie Michel

cs.AI

摘要

在过去几年中，在任意光照下合成神经辐射场（NeRFs）已成为一个重要问题。最近的研究通过提取基于物理的参数来解决这个问题，然后可以在任意光照下渲染，但它们在能处理的场景范围上受到限制，通常对光泽场景处理不当。我们提出了RRM，一种方法，即使在存在高反射物体的情况下，也可以提取场景的材质、几何和环境光照。我们的方法包括一个具有物理感知的辐射场表示，该表示指导基于物理的参数，以及基于拉普拉斯金字塔的富有表现力的环境光结构。我们证明了我们的贡献在参数检索任务上优于最先进技术，从而实现了在表面场景上高保真的重照和新视角合成。

English

Synthesizing NeRFs under arbitrary lighting has become a seminal problem in the last few years. Recent efforts tackle the problem via the extraction of physically-based parameters that can then be rendered under arbitrary lighting, but they are limited in the range of scenes they can handle, usually mishandling glossy scenes. We propose RRM, a method that can extract the materials, geometry, and environment lighting of a scene even in the presence of highly reflective objects. Our method consists of a physically-aware radiance field representation that informs physically-based parameters, and an expressive environment light structure based on a Laplacian Pyramid. We demonstrate that our contributions outperform the state-of-the-art on parameter retrieval tasks, leading to high-fidelity relighting and novel view synthesis on surfacic scenes.