Research map / 3D vision / Depth and stereo
Power Bundle Adjustment for Large-Scale 3D Reconstruction
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 a power-series expansion of the inverse Schur complement instead of competing solvers | Bundle adjustment on BAL · BAL, τ=0.1 and τ=0.01 | runtime and accuracy performance profile | Helped |
| Use a power-series expansion of the inverse Schur complement instead of competing solvers | Bundle adjustment on BAL · BAL, τ=0.003 | runtime and accuracy performance profile | Helped |
| Use a power-series expansion of the inverse Schur complement instead of competing solvers | Bundle adjustment on BAL · BAL, τ=0.001 | problems solved (%): 13% vs 54% at α = 1; 52% vs 88% at α = 3; 58% vs 98% at α = ∞ | Hurt |
| Replace dense LLᵀ factorization with PoBA for stochastic subproblems | STBA, forming PoST · BAL, τ=0.1, 0.01, and 0.003 | runtime and accuracy performance profile | Helped |
| Replace dense LLᵀ factorization with PoBA for stochastic subproblems | STBA, forming PoST · BAL, τ=0.001 | accuracy | No clear effect |
| Increase the power-series order m | Power-series preconditioner for CG · Ladybug-49 | total runtime | Hurt |
| Increase the power-series order m | Power-series preconditioner for CG · Ladybug-49 | CG iterations | Helped |
| Use PoBA-32 instead of PoBA-64 | PoBA · BAL, τ=0.001 | problems solved (%) at α=1: 13% -> 8% | Hurt |
Closest papers by meaning
- Square Root Bundle Adjustment for Large-Scale Reconstruction (CVPR 2021 · similarity 0.89)
- BA-T: An Iterative Transformer for Two-View Bundle Adjustment (NeurIPS 2026 · similarity 0.85)
- Matrix-Free Shared Intrinsics Bundle Adjustment (CVPR 2025 · similarity 0.83)
- BADGR: Bundle Adjustment Diffusion Conditioned by Gradients for Wide-Baseline Floor Plan Reconstruction (CVPR 2025 · similarity 0.81)
- SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting (CVPR 2025 · similarity 0.79)
- Depth-Guided Bundle Sampling for Efficient Generalizable Neural Radiance Field Reconstruction (CVPR 2025 · similarity 0.79)
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.