Enhancing Camera Position Estimation by Multi-view Pure Rotation Recognition and Automated Annotation Learning

Pure rotational anomaly recognition is a critical problem in 3D visual computation, requiring precise recognition for reliable camera pose estimation and robust 3D reconstruction. Current techniques primarily focus on model selection, parallax angle, and intersection constraints within two-view geometric models when identifying pure rotational motion. This paper proposes a multi-view pure rotational detection method that draws upon two-view rotation-only recognition indicators to identify pure rotational views that cause pose estimation anomalies. An automatic data annotation and training strategy for rotation-only anomaly recognition in multi-view pose estimation data is also introduced. Our experiments demonstrate that our proposed model for rotation-only anomaly recognition achieves an accuracy of 91% on the test set and is highly effective in improving the precision, resilience, and performance of camera pose estimation, 3D reconstruction, object tracking, and other computer vision tasks. The effectiveness of our approach is validated through comparison with related approaches in simulated camera motion trajectory experiments and Virtual KITTI dataset.