A fast local descriptor for dense matchingReport as inadecuate




A fast local descriptor for dense matching - Download this document for free, or read online. Document in PDF available to download.

Presented at: Conference on Computer Vision and Pattern Recognition, Alaska, USA, June 24-26, 2008 Publication date: 2008

We introduce a novel local image descriptor designed for dense wide-baseline matching purposes. We feed our descriptors to a graph-cuts based dense depth map estimation algorithm and this yields better wide-baseline performance than the commonly used correlation windows for which the size is hard to tune. As a result, unlike competing techniques that require many high-resolution images to produce good reconstructions, our descriptor can compute them from pairs of low-quality images such as the ones captured by video streams. Our descriptor is inspired from earlier ones such as SIFT and GLOH but can be computed much faster for our purposes. Unlike SURF which can also be computed efficiently at every pixel, it does not introduce artifacts that degrade the matching performance. Our approach was tested with ground truth laser scanned depth maps as well as on a wide variety of image pairs of different resolutions and we show that good reconstructions are achieved even with only two low quality images.

Keywords: descriptor ; depth estimation ; dense computation ; DAISY Reference EPFL-CONF-126372View record in Web of Science





Author: Tola, Engin; Lepetit, Vincent; Fua, Pascal

Source: https://infoscience.epfl.ch/record/126372?ln=en







Related documents