Research map / Probabilistic and scientific modeling / Variational and generative sampling
Robust Variational Bayesian Point Set Registration
Jie Zhou, Xinke Ma, Li Liang, Yang Yang, Shijin Xu, Yuhe Liu, Sim-Heng Ong
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 |
|---|---|---|---|
| use the proposed variational Bayesian registration instead of Yang et al. (strongest baseline) | Ours · GID image registration | RMSE: 11.85 -> 3.11 | Improved |
| use the proposed method instead of Yang et al. | Ours · GID image registration | MAE: 13.92 -> 4.41 | Improved |
| use the proposed method instead of Yang et al. | Ours · GID image registration | SD: 9.76 -> 1.39 | Improved |
| use the proposed method instead of CPD | Ours · GID image registration | RMSE: 87.33 -> 3.11 | Improved |
| use the proposed method instead of five baselines on 3D human motion capture (450 frames, 42 markers) | Ours · 3D human motion capture | mean absolute error / SD of error | Improved |
Closest papers by meaning
- Probabilistic Model for Robust Affine and Non-Rigid Point Set Matching (TPAMI 2016 · similarity 0.90)
- Robust Outlier Rejection for 3D Registration With Variational Bayes (CVPR 2023 · similarity 0.89)
- A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization (NeurIPS 2024 · similarity 0.86)
- Variational Inference with Mixtures of Isotropic Gaussians (NeurIPS 2025 · similarity 0.85)
- Uncertainty Estimation for Pretrained Medical Image Registration Models via Transformation Equivariance (NeurIPS 2026 · similarity 0.85)
- Scalable 3D Registration via Truncated Entry-wise Absolute Residuals (CVPR 2024 · 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.
