AI RESEARCH

Reliev3R: Relieving Feed-forward Reconstruction from Multi-View Geometric Annotations

arXiv CS.CV

ArXi:2604.00548v1 Announce Type: new With recent advances, Feed-forward Reconstruction Models (FFRMs) have nstrated great potential in reconstruction quality and adaptiveness to multiple downstream tasks. However, the excessive reliance on multi-view geometric annotations, e.g. 3D point maps and camera poses, makes the fully-supervised