Search papers, labs, and topics across Lattice.
Aalto University, Finland
3
0
2
45
HSA achieves up to 41.5% improvement in scene decomposition accuracy by leveraging hierarchical semantic understanding with minimal labeled data.
GeoMix slashes localization errors by up to 90% in descriptor-free visual matching, challenging the dominance of traditional descriptor-based approaches.
Stop forcing object-centric learning models into rigid feature alignment; cycle consistency works better when applied to the reconstructed visual scene.
