Research map / 3D vision / Human pose estimation
Leveraging Equivariant Features for Absolute Pose Regression
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 |
|---|---|---|---|
| Use an SE(2)-equivariant feature-extraction backbone instead of a classical CNN backbone | E-PoseNet · Cambridge Landmarks and 7-Scenes | median position error | Helped |
| Use an SE(2)-equivariant feature-extraction backbone instead of a classical CNN backbone | E-PoseNet · Cambridge Landmarks and 7-Scenes | median orientation error | Mixed |
| Increase rotational equivariance by using finer rotation sampling (ablation) | CNN pose estimator · T-Less object 5 training sequence | proportion of poses below 10cm, 10° error | Helped |
| Use continuous SO(2) rotation equivariance rather than discretely sampled rotations (ablation) | CNN pose estimator · T-Less object 5 training sequence | proportion of poses below 10cm, 10° error | Helped |
| Train without further data augmentation while using equivariant features | E-PoseNet · Cambridge Landmarks and 7-Scenes | median pose error | Mixed |
Closest papers by meaning
- Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction (ICLR 2023 · similarity 0.90)
- 3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction (NeurIPS 2024 · similarity 0.90)
- Pose-Transformed Equivariant Network for 3D Point Trajectory Prediction (CVPR 2024 · similarity 0.89)
- Neural Refinement for Absolute Pose Regression with Feature Synthesis (CVPR 2024 · similarity 0.88)
- Neural Isometries: Taming Transformations for Equivariant ML (NeurIPS 2024 · similarity 0.87)
- FAR: Flexible Accurate and Robust 6DoF Relative Camera Pose Estimation (CVPR 2024 · 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.