# CSS-BA: Gate-Guided Column Space Search for Bundle Adjustment

arXiv: https://arxiv.org/abs/2607.15652 · HTML: https://mlsanity.com/paper/2607.15652/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 31 references that are in the map.
- First posted on arXiv 17 Jul 2026.

## Builds on (most cited first, 12 of 12)

- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Global Structure-from-Motion Revisited](https://mlsanity.com/paper/2407.20219/) (2024)
- [MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion](https://mlsanity.com/paper/2409.19152/) (2024)
- [Stochastic Bundle Adjustment for Efficient and Scalable 3D Reconstruction](https://mlsanity.com/paper/2008.00446/) (2020)
- [Square Root Bundle Adjustment for Large-Scale Reconstruction](https://mlsanity.com/paper/2103.01843/) (2021)
- [MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment](https://mlsanity.com/paper/2112.01349/) (2021)
- [Revisiting Rolling Shutter Bundle Adjustment: Toward Accurate and Fast Solution](https://mlsanity.com/paper/2209.08503/) (2022)
- [Power Variable Projection for Initialization-Free Large-Scale Bundle Adjustment](https://mlsanity.com/paper/2405.05079/) (2024)
- [Bundle Adjustment in the Eager Mode](https://mlsanity.com/paper/2409.12190/) (2024)
- [InstantSfM: Towards GPU-Native SfM for the Deep Learning Era](https://mlsanity.com/paper/2510.13310/) (2025)
- [Towards Initialization-free Calibrated Bundle Adjustment](https://mlsanity.com/paper/2506.23808/) (2025)

## Abstract (arXiv)

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.