Homography-Based Loss Function for Camera Pose Regression. (arXiv:2205.01937v1 [cs.CV])

Web: http://arxiv.org/abs/2205.01937

Some recent visual-based relocalization algorithms rely on deep learning
methods to perform camera pose regression from image data. This paper focuses
on the loss functions that embed the error between two poses to perform deep
learning based camera pose regression. Existing loss functions are either
difficult-to-tune multi-objective functions or present unstable reprojection
errors that rely on ground truth 3D scene points and require a two-step
training. To deal with these issues, we introduce a novel loss function which
is based …

arxiv cv function homography loss regression