PURE: Refining Feed-forward 3D Reconstruction with Unlabeled Post-training

arXiv:2610.14698v1 Announce Type: new Abstract: 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 expensive depth and camera pose annotations, which hinders scaling to diverse real-world dynamic data and restricts generalization. To address this issue, we propose extbf{PURE}, an unlabeled post-training refinement framework that improves depth and camera estimation without requiring ground-truth supervision. Instead of relying on annotations, PURE elegantly distills robust structural knowledge from state-of-the-art 2D priors into 4D feed-forward architectures. PURE leverages relative depth constraints, affine-invariant geometry distillation, and pose refinement based on feature correspondences to stabilize geometric predictions under challenging dynamic conditions. Extensive experiments on both synthetic and real-world dynamic benchmarks demonstrate that PURE delivers consistent improvements across multiple state-of-the-art architectures. Furthermore, our data-efficient paradigm effectively mitigates domain shifts, successfully unlocking the architectural limits of these base models in challenging, in-the-wild dynamic scenes.

Related

• Dyna3: VLM-Guided Training-Free 4D Reconstruction via Depth Foundation Models
• Feed-Forward Gaussian Splatting from Sparse Aerial Views
• G3T Up! Gravity Aligned Coordinate Frames Simplify Pointmap Processing

Source: arXiv cs.CV | 2026-10-14