Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Learning Correspondence Uncertainty via Differentiable Nonlinear Least Squares
Dominik Muhle, Lukas Koestler, Krishna Murthy Jatavallabhula, Daniel Cremers
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 |
|---|---|---|---|
| learn feature-position covariances using differentiable pose optimization | PNEC relative pose estimation · KITTI test, SuperPoint | RPE_n: 5.353 -> 3.333 | Improved |
| learn feature-position covariances using differentiable pose optimization | PNEC relative pose estimation · KITTI test, KLT tracks | RPE_n: 3.060 -> 2.359 | Improved |
| use self-supervised cycle-consistency training instead of supervised pose training | learned covariance model · KITTI test, KLT tracks | RPE_n: 2.359 -> 1.910 | Improved |
| use a KITTI-trained self-supervised model on EuRoC | learned covariance model · EuRoC mean, SuperPoint | RPE_n: 58.90 -> 30.57 | Improved |
| use varied pose geometries during covariance learning (ablation) | synthetic covariance learning · synthetic experiments | 2D covariance estimation | Improved |
| use a single shared geometric setup rather than diverse pose geometries (ablation) | synthetic covariance learning · synthetic experiments | 2D covariance estimation | Hurt |
Closest papers by meaning
- From Correspondences to Pose: Non-minimal Certifiably Optimal Relative Pose without Disambiguation (CVPR 2024 · similarity 0.89)
- FAR: Flexible Accurate and Robust 6DoF Relative Camera Pose Estimation (CVPR 2024 · similarity 0.86)
- From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers (CVPR 2024 · similarity 0.85)
- Structure-Aware Correspondence Learning for Relative Pose Estimation (CVPR 2025 · similarity 0.85)
- Rethinking Correspondence-based Category-Level Object Pose Estimation (CVPR 2025 · similarity 0.85)
- 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation (ICLR 2024 · similarity 0.85)
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.
