Optimal Multi-view Correction of Local Affine Frames
This work addresses the need for more accurate affine frame estimation in computer vision applications, but it is incremental as it builds on existing detectors and methods.
The paper tackles the problem of correcting local affine frames from multi-view images by exploiting epipolar geometry constraints, resulting in improved accuracy for affine-covariant feature detectors and downstream tasks like pose estimation.
The technique requires the epipolar geometry to be pre-estimated between each image pair. It exploits the constraints which the camera movement implies, in order to apply a closed-form correction to the parameters of the input affinities. Also, it is shown that the rotations and scales obtained by partially affine-covariant detectors, e.g., AKAZE or SIFT, can be completed to be full affine frames by the proposed algorithm. It is validated both in synthetic experiments and on publicly available real-world datasets that the method always improves the output of the evaluated affine-covariant feature detectors. As a by-product, these detectors are compared and the ones obtaining the most accurate affine frames are reported. For demonstrating the applicability, we show that the proposed technique as a pre-processing step improves the accuracy of pose estimation for a camera rig, surface normal and homography estimation.