Research map / Point clouds / Registration and matching
Discriminative Optimization: Theory and Applications to Point Cloud Registration
Check 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 |
|---|---|---|---|
| Learn update directions from training examples instead of optimizing an explicit cost function | DO · Synthetic 3D registration | success rate | Helped |
| Learn update directions from training examples instead of optimizing an explicit cost function | DO · Synthetic 3D registration | computation time | Helped |
| Train on synthetic examples of the target object and apply the learned updates to cluttered scenes | DO · UWA range-scan registration | success rate | Helped |
| Train on synthetic examples of the target object and apply the learned updates to cluttered scenes | DO · UWA range-scan registration | computation time | Helped |
| Use learned updates for pose estimation across frames | DO · 3D object tracking | tracking accuracy | Helped |
| Use learned updates for pose estimation across frames | DO · 3D object tracking | computation time: 40ms per frame | Helped |
| Continue applying the final learned map until the update is small or the iteration limit is reached | DO · Point cloud registration | registration accuracy | Helped |
Closest papers by meaning
- Inverse Composition Discriminative Optimization for Point Cloud Registration (CVPR 2018 · similarity 0.89)
- A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization (NeurIPS 2024 · similarity 0.86)
- FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators (ICLR 2024 · similarity 0.86)
- PosDiffNet: Positional Neural Diffusion for Point Cloud Registration in a Large Field of View with Perturbations (AAAI 2024 · similarity 0.86)
- Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration (NeurIPS 2024 · similarity 0.86)
- Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy (ICLR 2025 · similarity 0.86)
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.