Photorealistic object appearance modeling from 2D images is a constant topic in vision and graphics. While neural implicit methods (such as Neural Radiance Fields) have shown high-fidelity view synthesis results, they cannot relight the captured objects. More recent neural inverse rendering approaches have enabled object relighting, but they represent surface properties as simple BRDFs, and therefore cannot handle translucent objects. We propose Object-Centric Neural Scattering Functions (OSFs) for learning to reconstruct object appearance from only images. OSFs not only support free-viewpoint object relighting, but also can model both opaque and translucent objects. While accurately modeling subsurface light transport for translucent objects can be highly complex and even intractable for neural methods, OSFs learn to approximate the radiance transfer from a distant light to an outgoing direction at any spatial location. This approximation avoids explicitly modeling complex subsurface scattering, making learning a neural implicit model tractable. Experiments on real and synthetic data show that OSFs accurately reconstruct appearances for both opaque and translucent objects, allowing faithful free-viewpoint relighting as well as scene composition. Project website: https://kovenyu.com/osf/

翻译：从二维图像中实现逼真的物体外观建模是视觉与图形学领域的持续研究课题。尽管神经隐式方法（如神经辐射场）已展现出高保真视角合成结果，但它们无法对已捕获物体进行重照明。近年来的神经逆渲染方法虽实现了物体重照明，但其将表面属性表示为简单的双向反射分布函数（BRDF），因此无法处理半透明物体。我们提出物体中心神经散射函数（OSFs），用于学习仅从图像重建物体外观。OSFs不仅支持自由视点物体重照明，还能同时对不透明与半透明物体进行建模。尽管半透明物体的次表面光传输建模极为复杂，甚至对神经方法而言亦可能难以处理，但OSFs学会逼近从远距离光源至任意空间位置出射方向的辐射传输。该近似方法避免了对复杂次表面散射的显式建模，使得神经隐式模型的学习变得可行。在真实与合成数据上的实验表明，OSFs能精确重建不透明与半透明物体的外观，实现高保真自由视点重照明及场景合成。项目网站：https://kovenyu.com/osf/