Spherical Harmonics are used as a basis for representing and decomposing spherical signals, such as high-dynamic-range (HDR) images or panoramic images. By decomposing spherical signals into spherical harmonics, practitioners can efficiently analyze, process, and transmit spherical data, making it easier to work with panoramic images and other forms of spherical visual information. This representation is particularly useful in computer graphics, computer vision, and applications involving spherical data, such as panoramic imaging.


GLoSH: Global-Local Spherical Harmonics for Intrinsic Image Decomposition

Traditional intrinsic image decomposition focuses on decomposing images into reflectance and shading, leaving surfaces normals and lighting entangled in shading. In this work, we propose a Global-Local Spherical Harmonics (GLoSH) lighting model to improve the lighting component, and jointly predict reflectance and surface normals. The global SH models the holistic lighting while local SH account for the spatial variation of lighting. Also, a novel non-negative lighting constraint is proposed to encourage the estimated SH to be physically meaningful. To seamlessly reflect the GLoSH model, we design a coarse-to-fine network structure. The coarse network predicts global SH, reflectance and normals, and the fine network predicts their local residuals. Lacking labels for reflectance and lighting, we apply synthetic data for model pre-training and fine-tune the model with real data in a self-supervised way. Compared to the state-of-the-art methods only targeting normals or reflectance and shading, our method recovers all components and achieves consistently better results on three real datasets, IIW, SAW and NYUv2.