Vittorio Ferrari, Tinne Tuytelaars, Luc Van Gool

Overview

Source code for the Image Exploration algorithm. This is a technique for automatically finding dense correspondences between multiple views of the same object or scene. The software is well suited for finding two-view correspondences as well.

This release covers the ECCV 2004 [1] and CVPR 2004 [2] papers. The technique was used in the CVPR 2006 [3] and IJRR 2009 [4] papers.

Downloads

References

1. Simutaneous Object Recognition and Segmentation by Image Exploration
   Vittorio Ferrari, Tinne Tuytelaars and Luc Van Gool,
   In European Conference in Computer Vision (ECCV), 2004.
2. Integrating Multiple Model Views for Object Recognition
   Vittorio Ferrari, Tinne Tuytelaars and Luc Van Gool,
   In Computer Vision and Pattern Recognition (CVPR), 2004.
3. Towards Multi-View Object Class Detection
   A. Thomas, V. Ferrari, B. Leibe, T. Tuytelaars, B. Schiele, L. Van Gool,
   In Computer Vision and Pattern Recognition (CVPR), 2006.
4. Using Multi-view Recognition and Meta-data Annotation to Guide a Robot’s
   Attention
   A. Thomas, V. Ferrari, B. Leibe, T. Tuytelaars, B. Schiele, L. Van Gool,
   In International Journal of Robotics Research (IJRR), 2009.