3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction
–Neural Information Processing Systems
To overcome these issues, we propose a frequency-domain approach that directly predicts Wigner-D coefficients for 3D rotation regression, aligning with the operations of spherical CNNs.
Neural Information Processing Systems
Oct-10-2025, 19:58:23 GMT
- Country:
- Asia
- Japan > Honshū
- Chūbu > Ishikawa Prefecture > Kanazawa (0.04)
- Middle East > Republic of Türkiye
- Karaman Province > Karaman (0.04)
- South Korea > Gyeongsangbuk-do
- Pohang (0.04)
- Japan > Honshū
- Europe (0.04)
- North America > United States
- California > Santa Clara County > Palo Alto (0.04)
- Asia
- Genre:
- Research Report > Experimental Study (1.00)
- Industry:
- Health & Medicine (0.67)
- Information Technology > Security & Privacy (0.46)
- Technology:
- Information Technology
- Artificial Intelligence
- Machine Learning
- Neural Networks > Deep Learning (0.68)
- Statistical Learning (0.93)
- Representation & Reasoning > Object-Oriented Architecture (0.67)
- Robots (0.68)
- Vision (1.00)
- Machine Learning
- Data Science (0.93)
- Artificial Intelligence
- Information Technology