Search papers, labs, and topics across Lattice.
This work was supported in part by the National Natural Science Foundation of China under Grant 62202234, 62372128, 62401270, 62502215, U22B2062, 62172232; China Postdoctoral Science Foundation under Grant 2023M741778; Natural Science Foundation of Guangdong Province under Grant 2023A1515011575; Nanjing Major Science and Technology Special Project under Grant 202405002. (Corresponding author: Zhangjie Fu
2
0
4
0
Forget messy SDFs and post-hoc hacks: PixARMesh directly generates artist-ready 3D scene meshes from a single image in one fell swoop.
DreamWorld achieves more world-consistent video generation by jointly modeling multiple heterogeneous dimensions of world knowledge, moving beyond surface-level plausibility.
