Preprint
Oct 2026
PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training
Feed-forward 3D reconstruction models have achieved remarkable progress through large-scale training and strong learned priors. However, they remain fragile when applied to dynamic in-the-wild videos, where non-rigid motion, occlusions, and illumination changes are prevalent. A key limitation lies in their reliance on...
Yao-Long Zhu, Peng Li, Jia-Hao Lu et al.
· 0 citations