Deep Inverse Rendering for Practical Object Appearance Scan with Uncalibrated Illumination

Jianzhao Zhang, Guojun Chen, Yue Dong, Jian Shi, Bob Zhang, Enhua Wu

Abstract: In this paper, we propose a practical method to estimate object appearance from an arbitrary number of images. We use a moving flashlight as light source, and encode surface reflectance properties in a pre-learned embedded latent space. Such lighting and appearance model combination enables our method to effectively narrow the solution space. Uncalibrated illumination requirement extremely simplifies our setup and affords it unnecessary to accurately locate light positions in advance. Moreover, our method automatically selects key frames before appearance estimation, which largely reduces calculation cost. Both synthetic and real experiments demonstrate that our method can recover object appearance accurately and conveniently.