CSS-BA: Gate-Guided Column Space Search for Bundle Adjustment
Computer Vision and Pattern Recognition
Summary
The authors address a problem in 3D image reconstruction where traditional methods struggle when camera movement is small or mostly rotational. They introduce Gate-Guided CSS-BA, an improved algorithm that keeps the original problem setup but restricts steps to a smarter, geometry-based direction, making the calculations more stable. Unlike other methods that simplify the problem by removing some variables, their approach keeps everything but changes only how updates are made. Tests show this results in more reliable camera positioning and calibration without losing accuracy in the images.
Authors
Ayano Kaneda, Takafumi Taketomi, Shugo Yamaguchi, Shigeo Morishima
Abstract
Bundle adjustment (BA) remains a critical refinement module for image-based 3D reconstruction and continues to improve geometric accuracy even in learning-based pipelines. However, in low-parallax and near-rotational regimes, classical Schur-based Levenberg--Marquardt (LM) often becomes ill-conditioned and yields unreliable pose and calibration estimates. We propose Gate-Guided CSS-BA, a solver-side modification of Schur-LM that preserves the classical BA objective and trust-region framework while constraining each update to a geometrically informed low-dimensional subspace. By integrating Column Space Search (CSS) with geometry-aware gating, the method stabilizes the Schur-LM update without altering the estimation problem. In contrast to keyframe or state-selection approaches, all camera and point parameters remain in the optimization problem; only the update direction is restricted. The method serves as a drop-in replacement for existing BA pipelines. Experiments on both generic and challenging weak-geometry scenarios show more stable optimization, improved relative pose accuracy, and competitive calibration behavior while maintaining reprojection quality.