High-quality Shape from Multi-view Stereo and Shading under General Illumination

Chenglei Wu1,3       Bennett Wilburn2       Yasuyuki Matsushita2       Christian Theobalt1      

1MPI Informatik      2Microsoft Research Asia      3Intel Visual Computing Institute

Input frame


Multi-view stereo methods reconstruct 3D geometry from images well for sufficiently textured scenes, but often fail to recover high-frequency surface detail, particularly for smoothly shaded surfaces. On the other hand, shape-fromshading methods can recover fine detail from shading variations. Unfortunately, it is non-trivial to apply shape-fromshading alone to multi-view data, and most shading-based estimation methods only succeed under very restricted or controlled illumination. We present a new algorithm that combines multi-view stereo and shading-based refinement for high-quality reconstruction of 3D geometry models from images taken under constant but otherwise arbitrary illumination. We have tested our algorithm on several scenes that were captured under several general and unknown lighting conditions, and we show that our final reconstructions rival laser range scans.


In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 969-976, 2011: PDF

Data Sets

In case you use this data for a publication, include a citation to our paper (bibtex).

Each data set provides a sequence of input images in BMP format, a calibration file and a reconstructed mesh in OFF format. Please read [this text] before you start to download the data.

angel data set
Angel: [Input Images] [Calibration File] [Reconstructed Mesh]

fish data set
Fish: [Input Images] [Calibration File] [Reconstructed Mesh]

paper data set
Paper: [Input Images] [Calibration File] [Reconstructed Mesh]