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

Chenglei Wu^1,3       Bennett Wilburn²       Yasuyuki Matsushita²       Christian Theobalt¹      

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

Abstract

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.

Paper

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: [Input Images] [Calibration File] [Reconstructed Mesh]

Fish: [Input Images] [Calibration File] [Reconstructed Mesh]

Paper: [Input Images] [Calibration File] [Reconstructed Mesh]