3 papers
cs.CV2026
Does the VGGT Family Need All Its Layers?
Fengyi Zhang, Holger Caesar, Xiangyu Sun +3
Which layers of a feed-forward geometry model are needed to preserve both camera poses and dense 3D structure? We study layer redundancy in VGGT, , and VGGT-: 3,018 pruned…
cs.CV2025
TALO: Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstruction
Fengyi Zhang, Tianjun Zhang, Kasra Khosoussi +3
3D vision foundation models have shown strong generalization in reconstructing key 3D attributes from uncalibrated images through a single feed-forward pass. However, when deployed…
cs.CV2025
Test-Time 3D Occupancy Prediction
Fengyi Zhang, Xiangyu Sun, Huitong Yang +3
Self-supervised 3D occupancy prediction offers a promising solution for understanding complex driving scenes without requiring costly 3D annotations. However, training dense occupa…