A Variational Approach to Shape-from-shading Under Natural Illumination
This work addresses shape recovery from shading in computer vision, but appears incremental as it builds on existing PDE-based models.
The paper tackled shape-from-shading under natural illumination by presenting a numerical solution based on an augmented Lagrangian approach, enabling applications like depth map denoising and refinement.
A numerical solution to shape-from-shading under natural illumination is presented. It builds upon an augmented Lagrangian approach for solving a generic PDE-based shape-from-shading model which handles directional or spherical harmonic lighting, orthographic or perspective projection, and greylevel or multi-channel images. Real-world applications to shading-aware depth map denoising, refinement and completion are presented.