Search papers, labs, and topics across Lattice.
2
0
4
Ditch the per-ray prediction bottleneck: NOVA3R's global scene representation and diffusion-based decoder unlock more complete and accurate 3D reconstructions from unposed images.
By predicting camera-space scene flow directly, Flow4R elegantly unifies 3D reconstruction, object motion, and camera motion without explicit pose regressors or bundle adjustment.
