Towards Initialization-free Calibrated Bundle Adjustment

TL;DR

This paper introduces a method for calibrated bundle adjustment that leverages known camera calibration and pairwise relative rotation estimates to achieve near metric reconstructions without initialization.

Contribution

It integrates rotation averaging into the pOSE framework to enable initialization-free calibrated structure-from-motion with high reliability.

Findings

Achieves convergence to the global minimum from random initializations.

Produces accurate near metric reconstructions using known camera calibration.

Successfully incorporates rotation information to improve reconstruction quality.

Abstract

A recent series of works has shown that initialization-free BA can be achieved using pseudo Object Space Error (pOSE) as a surrogate objective. The initial reconstruction-step optimizes an objective where all terms are projectively invariant and it cannot incorporate knowledge of the camera calibration. As a result, the solution is only determined up to a projective transformation of the scene and the process requires more data for successful reconstruction. In contrast, we present a method that is able to use the known camera calibration thereby producing near metric solutions, that is, reconstructions that are accurate up to a similarity transformation. To achieve this we introduce pairwise relative rotation estimates that carry information about camera calibration. These are only invariant to similarity transformations, thus encouraging solutions that preserve metric features of the real scene. Our method can be seen as integrating rotation averaging into the pOSE framework striving towards initialization-free calibrated SfM. Our experimental evaluation shows that we are able to reliably optimize our objective, achieving convergence to the global minimum with high probability from random starting solutions, resulting in accurate near metric reconstructions.