We present a novel approach for digitizing real-world objects by estimating their geometry, material properties, and environmental lighting from a set of posed images with fixed lighting. Our method incorporates into Neural Radiance Field (NeRF) pipelines the split sum approximation used with image-based lighting for real-time physical-based rendering. We propose modeling the scene's lighting with a single scene-specific MLP representing pre-integrated image-based lighting at arbitrary resolutions. We achieve accurate modeling of pre-integrated lighting by exploiting a novel regularizer based on efficient Monte Carlo sampling. Additionally, we propose a new method of supervising self-occlusion predictions by exploiting a similar regularizer based on Monte Carlo sampling. Experimental results demonstrate the efficiency and effectiveness of our approach in estimating scene geometry, material properties, and lighting. Our method is capable of attaining state-of-the-art relighting quality after only ${\sim}1$ hour of training in a single NVIDIA A100 GPU.

翻译：我们提出一种新颖方法，通过一组固定光照下的姿态图像来数字化真实世界物体，同时估计其几何形状、材质属性与环境光照。本方法将图像光照中用于实时物理渲染的分裂求和近似技术融入神经辐射场（NeRF）管线。我们通过一个场景专属的MLP表示任意分辨率的预集成图像光照，从而实现场景光照建模。通过基于高效蒙特卡洛采样的新型正则化器，我们实现了对预集成光照的精确建模。此外，我们提出一种利用类似蒙特卡洛采样正则化器监督自遮挡预测的新方法。实验结果表明，本方法在估计场景几何、材质属性与光照方面兼具高效性与有效性。在单个NVIDIA A100 GPU上仅需约1小时训练即可达到当前最先进的重新照明质量。