Variational Perspective Shape from Shading

Yong Chul Ju, Andrés Bruhn, Michael Breuß

Abstract: Many recent methods for perspective shape from shading (SfS) are based on formulations in terms of partial differential equations (PDEs). However, while the quality of such methods steadily improves, their lacking robustness is still an open issue. In this context, variational methods seem to be a promising alternative, since they allow to incorporate smoothness assumptions that have proven to be useful for many other tasks in computer vision. Surprisingly, however, such methods have hardly been considered for perspective SfS so far. In our article we address this problem and develop a novel variational model for this task. By combining building blocks of recent PDE-based methods such as a Lambertian reflectance model and camera-centred illumination with a discontinuity-preserving second-order smoothness term, we obtain a variational method for perspective SfS that offers by construction an improved degree of robustness compared to existing PDE-based approaches. Our experiments confirm the success of our strategy. They show that embedding the assumptions of PDE-based approaches into a variational model with a suitable smoothness term can be very beneficial – in particular in scenarios with noise or partially missing information.