Combining Cues: Shape from Shading and Texture

We demonstrate a method for reconstructing the shape of a deformed surface from a single view. After decomposing an image into irradiance and albedo components, we combine normal cues from shading and texture to produce a field of unambiguous normals. Using these normals, we reconstruct the 3D geometry. Our method works in two regimes: either requiring the frontal appearance of the texture or building it automatically from a series of images of the deforming texture. We can recover geometry with errors below four percent of object size on arbitrary textures, and estimate specific geometric parameters using a custom texture even more accurately.

R. White, D.A. Forsyth "Combining Cues: Shape from Shading and Texture", IEEE Conference on Computer Vision and Pattern Recognition, 2006.

    author = {R. White and D.A. Forsyth},
    title = {Combining Cues: Shape from Shading and Texture},
    booktitle = {Computer Vision and Pattern Recognition},
    year = {2006},

Ryan White, D.A. Forsyth "Combining Cues: Shape from Shading and Texture", Technical Report No. EECS-2005-14, EECS Department, University of California, Berkeley, 2005.

Example: Known Texture

Observed image, with shading and known texture

Rerendered from new viewpoint.

Video [DIVX 2.9 MB]

Reconstructed points: red is from single view geometry, blue from multi-view geometry. Green lines denote errors.

Video [DIVX 6.7 MB]