Research map / 3D vision / Depth and stereo
expOSE: Accurate Initialization-Free Projective Factorization Using Exponential Regularization
José Pedro Iglesias, Amanda Nilsson, Carl Olsson
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Replace pOSE affine regularization with exponential regularization (expOSE) | projective factorization (pOSE) · Dino/Fountain convergence and 3D error | 3D error and convergence rate | Mixed |
| Delay update of quadratic regularization approximation by 250 iterations or until initial convergence (scheduling) (ablation) | expOSE · Dino (Small) and Fountain | convergence rate | Improved |
| Use VarPro instead of LM or AltMin for optimization (ablation) | expOSE · Dino (Small) and Fountain | convergence rate | Improved |
| Set radial weighting α=0.999 instead of α=1 in radial-invariant expOSE (ablation) | expOSE radial pipeline · Grossmunster | convergence rate and reprojection error | Hurt |
| Use α=1 (radial-only error dropped) instead of α=0.999 in radial pipeline (ablation) | expOSE radial pipeline · Munsterhof and Kirchenge | factorization 2D reprojection error | Improved |
| Apply bundle adjustment refinement (up to 50 iterations) after expOSE factorization | expOSE α=1 pipeline · Grossmunster, Kirchenge, Munsterhof | 2D reprojection error | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- pOSE — pOSE: Pseudo Object Space Error for Initialization-Free Bundle Adjustment (CVPR 2018) · better on 5 of 7 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- pOSE: Pseudo Object Space Error for Initialization-Free Bundle Adjustment (CVPR 2018 · similarity 0.90)
- Radial Distortion Invariant Factorization for Structure From Motion (ICCV 2021 · similarity 0.88)
- BA-T: An Iterative Transformer for Two-View Bundle Adjustment (NeurIPS 2026 · similarity 0.84)
- Matrix-Free Shared Intrinsics Bundle Adjustment (CVPR 2025 · similarity 0.84)
- From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers (CVPR 2024 · similarity 0.84)
- BADGR: Bundle Adjustment Diffusion Conditioned by Gradients for Wide-Baseline Floor Plan Reconstruction (CVPR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
