Search papers, labs, and topics across Lattice.
SJTU Abstract
2
0
3
PVCap achieves a remarkable 11.41% improvement over the state-of-the-art in 3D dense captioning by leveraging innovative data augmentation and a voxel-based architecture.
T2LDM++ generates realistic LiDAR scenes with rich geometric details, overcoming the limitations of existing models that struggle with insufficient training data and controllability.
