Initialization-Free Bundle Adjustment Revisited: A Controlled Experimental Study
2026-08-18 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors study a new method called Initialization-free bundle adjustment (InitFree BA), which tries to figure out camera positions and 3D scene shapes directly from pictures without needing a starting guess. They find that even if the math looks good (low error values), the actual 3D shapes can be quite off after certain corrections. They identify factors like starting assumptions, how many landmarks are seen, and how stable the corrections are as important for success. Their work provides tools and a testing setup to better understand and improve InitFree BA in the future.
Bundle AdjustmentStructure-from-MotionCamera Pose EstimationObject-Space ErrorVariable ProjectionProjective ReconstructionMetric Upgrade3D Scene ReconstructionOptimizationGround Truth Data
Authors
Simon Weber, Mateo de Mayo, Je Hyeong Hong, Carl Olsson, Daniel Cremers, Ronald Clark
Abstract
Initialization-free bundle adjustment (InitFree BA) aims to recover camera poses and scene structure directly from image observations, avoiding the geometric initialization stages of conventional structure-from-motion pipelines. Recent methods based on Object-Space Error (OSE) formulations and Variable Projection (VarPro) show encouraging optimization behavior from random camera configurations. However, existing evaluations primarily measure optimization success, leaving unclear whether a low OSE objective yields a valid metric 3D reconstruction. We revisit InitFree BA experimentally through a unified evaluation framework combining a C++ implementation of existing OSE formulations with a Blender-based dataset generator providing exact ground truth and controlled camera configurations and observation densities. Our experiments reveal a previously overlooked optimization--reconstruction gap: projective solutions with similarly low OSE values can lead to substantially different Euclidean reconstructions after metric upgrade. We identify initialization priors, landmark observation density, and metric-upgrade stability as key factors governing reconstruction success. Overall, our results suggest that the main challenge of InitFree BA is not merely minimizing OSE objectives, but obtaining projective reconstructions that admit reliable metric upgrade. We believe that the proposed benchmark, implementation, and analysis establish stronger experimental foundations for future research on initialization-free bundle adjustment, a problem largely unexplored within the computer vision community. Project page is available at https://github.com/simonwebertum/InitFreeBA.git.