CVJun 30, 2025

Towards Initialization-free Calibrated Bundle Adjustment

arXiv:2506.23808v11 citationsh-index: 2
Originality Incremental advance
AI Analysis

This work addresses the need for more accurate and reliable structure-from-motion without requiring initial guesses, though it is incremental by building on the pOSE framework.

The paper tackles the problem of initialization-free bundle adjustment by incorporating known camera calibration to produce near metric reconstructions, achieving convergence to the global minimum with high probability from random starts.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes