Initialization-Free Bundle Adjustment Revisited: A Controlled Experimental Study

• URL: http://arxiv.org/abs/2608.18028v1
• Date: Tue, 18 Aug 2026 17:23:06 GMT
• Title: Initialization-Free Bundle Adjustment Revisited: A Controlled Experimental Study
• Abstract summary: Initialization-free bundle adjustment (InitFree BA) aims to recover camera poses and scene structure directly from image observations.<n>Recent methods based on Object-Space Error (OSE) formulations and Variable Projection (VarPro) show encouraging optimization behavior from random camera configurations.<n>We revisit InitFree BA experimentally through a unified evaluation framework combining a C++ implementation of existing OSE formulations with a Blender-based dataset generator.
• Score: 55.50399455527231
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Confidence matters: Leveraging Multi-view Geometric Priors for GS-based Reconstruction [28.891336184070223]
  3D Gaussian splatting (3DGS) has emerged as a widely-used tool for novel view synthesis, offering real-time rendering in a sparse representation.<n>We investigate the integration of geometric priors, in the form of predicted normal and depth maps, into the 3DGS framework to improve the reconstruction quality.
  arXiv  Detail & Related papers  (2026-08-06T14:50:29Z)
• DeepBias: Adaptive In-depth Probing of Social Biases in LVLMs [71.85279836937578]
  We introduce DeepBias, an adaptive framework for the in-depth probing of social biases in LVLMs with carefully designed agents.<n>We build a benchmark named DeepBiasBench using our framework. By employing an ensemble of five diverse state-of-the-art LVLMs as anchors, the benchmark captures vulnerabilities shared across architectures.
  arXiv  Detail & Related papers  (2026-07-13T08:19:09Z)
• Evaluation-driven Scaling for Scientific Discovery [77.20820317940581]
  We introduce Simple Test-time Evaluation-driven Scaling (SimpleTES), a framework that combines parallel exploration, feedback-driven refinement, and local selection.<n>We find substantial gains unlocked by scaling evaluation-driven discovery loops along the right dimensions.<n>Our results establish effective evaluation-driven loop scaling as a central axis for advancing scientific discovery.
  arXiv  Detail & Related papers  (2026-04-21T11:24:09Z)
• OUGS: Active View Selection via Object-aware Uncertainty Estimation in 3DGS [14.124481717283544]
  OUGS is a principled, physically-grounded uncertainty formulation for 3DGS.<n>Our core innovation is to derive uncertainty directly from the explicit physical parameters of the 3D Gaussian primitives.<n>This foundation allows us to then seamlessly integrate semantic segmentation masks to produce a targeted, object-aware uncertainty score.
  arXiv  Detail & Related papers  (2025-11-12T15:08:46Z)
• Towards Initialization-free Calibrated Bundle Adjustment [8.698137120086065]
  We present a method that is able to use the known camera calibration thereby producing near metric solutions.<n>Our method can be seen as integrating rotation averaging into the pOSE framework.
  arXiv  Detail & Related papers  (2025-06-30T12:55:44Z)
• Improving Monocular Visual-Inertial Initialization with Structureless Visual-Inertial Bundle Adjustment [0.36868085124383626]
  We propose a structureless visual-inertial bundle adjustment to further refine previous structureless solution.<n>Experiments on real-world datasets show our method significantly improves the VIO initialization accuracy, while maintaining real-time performance.
  arXiv  Detail & Related papers  (2025-02-23T14:55:40Z)
• UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image [86.7128543480229]
  Unseen object pose estimation methods often rely on CAD models or multiple reference views.<n>To simplify reference acquisition, we aim to estimate the unseen object's pose through a single unposed RGB-D reference image.<n>We present a novel approach and benchmark, termed UNOPose, for unseen one-reference-based object pose estimation.
  arXiv  Detail & Related papers  (2024-11-25T05:36:00Z)
• Power Variable Projection for Initialization-Free Large-Scale Bundle Adjustment [39.997922776362174]
  We introduce Power Variable Projection (PoVar) to solve small-scale Bundle Adjustment problems. We experimentally demonstrate that our solver achieves state-of-the-art results in terms of speed and accuracy.
  arXiv  Detail & Related papers  (2024-05-08T14:22:39Z)
• Making Reconstruction-based Method Great Again for Video Anomaly Detection [64.19326819088563]
  Anomaly detection in videos is a significant yet challenging problem. Existing reconstruction-based methods rely on old-fashioned convolutional autoencoders. We propose a new autoencoder model for enhanced consecutive frame reconstruction.
  arXiv  Detail & Related papers  (2023-01-28T01:57:57Z)
• Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints [80.60538408386016]
  Estimating relative camera poses from consecutive frames is a fundamental problem in visual odometry. We propose an end-to-end trainable framework consisting of learnable modules for detection, feature extraction, matching and outlier rejection.
  arXiv  Detail & Related papers  (2020-07-29T21:41:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.