ImageNet3D: Towards General-Purpose Object-Level 3D Understanding Wufei Ma
–Neural Information Processing Systems
A vision model with general-purpose object-level 3D understanding should be capable of inferring both 2D ( e.g., class name and bounding box) and 3D information ( e.g., 3D location and 3D viewpoint) for arbitrary rigid objects in natural
Neural Information Processing Systems
Feb-17-2026, 10:55:34 GMT
- Country:
- Europe
- Germany > Baden-Württemberg
- Freiburg (0.04)
- Netherlands > North Holland
- Amsterdam (0.04)
- Switzerland > Zürich
- Zürich (0.14)
- Germany > Baden-Württemberg
- North America
- Canada (0.04)
- United States > Illinois
- Champaign County > Urbana (0.04)
- South America > Brazil (0.04)
- Europe
- Genre:
- Research Report (0.94)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning > Neural Networks (0.46)
- Natural Language > Large Language Model (0.68)
- Representation & Reasoning (0.93)
- Vision (1.00)
- Information Technology > Artificial Intelligence