zhangganlin/vista_slam
Image-to-3D • Updated • 1
Ganlin Zhang
zhangganlin
AI & ML interests
3D Vision
Recent Activity
authored a paper 1 day ago
Flow4R: Unifying 4D Reconstruction and Tracking with Scene Flow authored a paper 1 day ago
NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction authored a paper 2 days ago
BA-T: An Iterative Transformer for Two-View Bundle AdjustmentOrganizations
