Fua, P., & Leclerc, Y. G. (1994, May). Using 3-dimensional meshes to combine image-based and geometry-based constraints. In European Conference on Computer Vision (pp. 281-291). Springer, Berlin, Heidelberg.
A unified framework for 3-D shape reconstruction allows us to combine image-based and geometry-based information sources. The image information is akin to stereo and shape-from-shading, while the geometric information may be provided in the form of 3-D points, 3-D features or 2-D silhouettes.