CaSPR: LearningCanonicalSpatiotemporal PointCloudRepresentations
–Neural Information Processing Systems
Different from previous work, CaSPR learns representations thatsupport spacetime continuity,arerobusttovariable andirregularly spacetime-sampled point clouds, and generalize to unseen object instances. Our approach divides the problem into two subtasks.
Neural Information Processing Systems
Feb-9-2026, 13:46:42 GMT
- Country:
- Asia > Japan
- Honshū > Chūbu > Ishikawa Prefecture > Kanazawa (0.04)
- North America
- Asia > Japan
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning (1.00)
- Vision (0.69)
- Information Technology > Artificial Intelligence