Revisiting Rotation Averaging: Uncertainties and Robust Losses

Rotation error = 0.05 • , Translation error = 6.30 • (b) Uncertainty = 7.61 Rotation error = 4.81 • , Translation error = 21.12 • Figure 1. Two example pairs where, even though the relative pose estimation found a large number of correct inliers (shown by green line segments), the quality of the estimated poses differs greatly. The uncertainties, used as weighting terms, help in rotation averaging to account for this quality difference. Here, the shown numbers as the uncertainties are the traces of the covariance matrices.