Non-Rigid Photometric Stereo with Colored Lights

Example reconstruction

Example input image from dancing video

Example 3D reconstruction

Abstract

We present an algorithm and the associated capture methodology to acquire and track the detailed 3D shape, bends, and wrinkles of deforming surfaces. Moving 3D data has been difficult to obtain by methods that rely on known surface features, structured light, or silhouettes. Multispectral photometric stereo is an attractive alternative because it can recover a dense normal field from an un-textured surface. We show how to capture such data and register it over time to generate a single deforming surface.

Experiments were performed on video sequences of untextured cloth, filmed under spatially separated red, green, and blue light sources. Our first finding is that using zero-depth-silhouettes as the initial boundary condition already produces rather smoothly varying per-frame reconstructions with high detail. Second, when these 3D reconstructions are augmented with 2D optical flow, one can register the first frame’s reconstruction to every subsequent frame.

Paper

Non-Rigid Photometric Stereo with Colored Lights
Carlos Hernández, George Vogiatzis, Gabriel J. Brostow, Björn Stenger, Roberto Cipolla
Toshiba Research Europe and University of Cambridge
Published in ICCV 2007

poster [paper pdf, 5.5 MB]

poster [poster pdf, 1.1MB]

BibTeX

@INPROCEEDINGS{HernandezEtc_ICCV07,
 author = {Hern\'andez, C. and Vogiatzis, G. and Brostow, G. J. and Stenger, B. and Cipolla, R.},
 title =  {Non-Rigid Photometric Stereo with Colored Lights},
 booktitle = {Proc. of the 11th IEEE Intl. Conf. on Comp. Vision (ICCV)},
 location = {Rio de Janeiro, Brazil},
 year = 2007
}