Search papers, labs, and topics across Lattice.
University of Amsterdam, Aristotle University of Thessaloniki
2
0
3
IMAGIN-4D enables unprecedented fine-grained control over human-object interactions by leveraging spatio-temporal image conditioning, outperforming traditional methods that rely on single-token representations.
Ditch sparse contact cues: LEXIS-Flow uses a learned manifold of interaction signatures to capture dense, continuous proximity between humans and objects, leading to more realistic 3D HOI reconstructions.
