Research map / 3D vision / Depth and stereo
pOSE: Pseudo Object Space Error for Initialization-Free Bundle Adjustment
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use pOSE rather than GPRT constraints in the first-stage objective (ablation) | Initialization-free BA pipeline · Real SfM datasets in Table 3 | SRF | Helped |
| Use pOSE rather than GPRT constraints in the first-stage objective (ablation) | Initialization-free BA pipeline · Castle-P19 and Castle-P30 | SRF: Castle-P19: 88 vs 0; Castle-P30: 100 vs 0 | Helped |
| Use pOSE rather than GPRT constraints in the first-stage objective (ablation) | Initialization-free BA pipeline · Fountain-P11 | SRF: 100 vs 30 | Helped |
| Use pOSE rather than GPRT constraints in the first-stage objective (ablation) | Initialization-free BA pipeline · Entry-P10 | SRF: 98 vs 5 | Helped |
| Use pOSE rather than GPRT constraints in the first-stage objective (ablation) | Initialization-free BA pipeline · Alcatraz courtyard | SRF: 100 vs 0 | Helped |
| Use pOSE rather than GPRT constraints in the first-stage objective (ablation) | Initialization-free BA pipeline · Pumpkin | SRF: 100 vs 0 | Helped |
Closest papers by meaning
- From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers (CVPR 2024 · similarity 0.85)
- Matrix-Free Shared Intrinsics Bundle Adjustment (CVPR 2025 · similarity 0.83)
- BA-T: An Iterative Transformer for Two-View Bundle Adjustment (NeurIPS 2026 · similarity 0.83)
- Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis (NeurIPS 2024 · similarity 0.82)
- BADGR: Bundle Adjustment Diffusion Conditioned by Gradients for Wide-Baseline Floor Plan Reconstruction (CVPR 2025 · similarity 0.82)
- REACTO: Reconstructing Articulated Objects from a Single Video (CVPR 2024 · similarity 0.82)
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.