stereophotogrammetry is an emerging technique of scene understanding. Its
origins go back to at least the 1800s when people first started to investigate
using photographs to measure the physical properties of the
本文提出了一种从 360 度立体图像中估计场景高清空间变化光照、反射和几何的方法,该方法利用全景图像获得场景的详细几何信息,结合物理约束共同估计场景属性。通过重建场景的近场光环境、运用深度学习模型推断反射率和表面法线,加入光照与几何之间的物理约束以改进场景的反射率,实验结果表明该方法在增强现实应用中具有 State of the art 的性能有优势。