End2End Multi-View Feature Matching using Differentiable Pose Optimization. (arXiv:2205.01694v1 [cs.CV])

Web: http://arxiv.org/abs/2205.01694

Learning-based approaches have become indispensable for camera pose
estimation. However, feature detection, description, matching, and pose
optimization are often approached in an isolated fashion. In particular,
erroneous feature matches have severe impact on subsequent camera pose
estimation and often require additional measures such as outlier rejection. Our
method tackles this challenge by addressing feature matching and pose
optimization jointly: first, we integrate information from multiple views into
the matching by spanning a graph attention network across multiple frames to
predict …

arxiv cv optimization