Separating Texture and Illumination for Single-Shot Structured Light Reconstruction

Minh Vo, Srinivasa G. Narasimhan, Yaser Sheikh; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2014, pp. 427-434

Abstract


Active illumination based methods have a trade-off between acquisition time and resolution of the estimated 3D shapes. Multi-shot approaches can generate dense reconstructions but require stationary scenes. In contrast, single-shot methods are applicable to dynamic objects but can only estimate sparse reconstructions and are sensitive to surface texture. In this work, we develop a single-shot approach to produce dense reconstructions of highly textured objects. The key to our approach is an image decomposition scheme that can recover the illumination and the texture images from their mixed appearance. Despite the complex appearances of the illuminated textured regions, our method can accurately compute per pixel warps from the illumination pattern and the texture template to the observed image. The texture template is obtained by interleaving the projection sequence with an all-white pattern. Our estimated warping functions are reliable even with infrequent interleaved projection. Thus, we obtain detailed shape reconstruction and dense motion tracking of the textured surfaces. We validate the approach on synthetic and real data containing subtle non-rigid surface deformations.

Related Material


[pdf]
[bibtex]
@InProceedings{Vo_2014_CVPR_Workshops,
author = {Vo, Minh and Narasimhan, Srinivasa G. and Sheikh, Yaser},
title = {Separating Texture and Illumination for Single-Shot Structured Light Reconstruction},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2014}
}