ContactField: Implicit Field Representation for Multi-Person Interaction Geometry
–Neural Information Processing Systems
We introduce a novel implicit field representation tailored for multi-person interaction geometry in 3D spaces, capable of simultaneously reconstructing occupancy, instance identification (ID) tags, and contact fields. Volumetric representation of interacting human bodies presents significant challenges, including inaccurately captured geometries, varying degrees of occlusion, and data scarcity. Existing multi-view methods, which either reconstruct each subject in isolation or merge nearby 3D surfaces into a single unified mesh, often fail to capture the intricate geometry between interacting bodies and exploit on datasets with many views and a small group of people for training.
Neural Information Processing Systems
Mar-20-2025, 02:41:48 GMT
- Country:
- Africa > Cameroon
- Gulf of Guinea (0.15)
- Asia > South Korea (0.14)
- Africa > Cameroon
- Genre:
- Research Report > Experimental Study (1.00)
- Industry:
- Information Technology > Security & Privacy (0.67)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning > Neural Networks (1.00)
- Natural Language (0.93)
- Vision (1.00)
- Information Technology > Artificial Intelligence