Robust Image Matching Preserving Global Consistency
Yasushi Kanazawa, Kenichi Kanatani · 2003
We present a new method for detecting point matches between two images. While existing methods propagate local smoothness by iterations, our method imposes non-local constraints that should be approximately satisfied across the image. We define the “confidence” of such “soft constraints ” to all potential matches. The confidence is progressively updated by “mean-field approximation”. Finally, the “hard ” epipolar constraint is imposed by RANSAC. Using real images, we demonstrate that our method is robust to camera rotations and zooming changes. 1.