Search papers, labs, and topics across Lattice.
3
0
4
Achieve state-of-the-art novel view synthesis by disentangling 3D Gaussian Splatting from 2D image dependencies.
Ditch the expensive 3D annotations: Reliev3R trains high-quality 3D reconstruction models from scratch using only monocular relative depths and sparse image correspondences.
Text-heavy fine-tuning is blinding your MLLM to crucial 3D spatial information, but GAP-MLLM's geometry-aligned pre-training can restore its sight.
