Domes to Drones: Self-Supervised Active Triangulation for 3D Human Pose Reconstruction
–Neural Information Processing Systems
In contrast, 3d pose estimation from a single image is ill-posed due to occlusion and depth ambiguities.
Neural Information Processing Systems
Feb-14-2026, 00:45:25 GMT
- Country:
- Asia > Japan
- Honshū > Chūbu > Ishikawa Prefecture > Kanazawa (0.04)
- North America > Canada (0.04)
- Asia > Japan
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning (1.00)
- Robots > Humanoid Robots (0.42)
- Vision > Video Understanding (0.35)
- Information Technology > Artificial Intelligence