English

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

Computer Vision and Pattern Recognition 2026-04-02 v1

Abstract

With recent advances, Feed-forward Reconstruction Models (FFRMs) have demonstrated 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 training scheme of FFRMs difficult to scale up. In this paper, we propose Reliev3R, a weakly-supervised paradigm for training FFRMs from scratch without cost-prohibitive multi-view geometric annotations. Relieving the reliance on geometric sensory data and compute-exhaustive structure-from-motion preprocessing, our method draws 3D knowledge directly from monocular relative depths and image sparse correspondences given by zero-shot predictions of pretrained models. At the core of Reliev3R, we design an ambiguity-aware relative depth loss and a trigonometry-based reprojection loss to facilitate supervision for multi-view geometric consistency. Training from scratch with the less data, Reliev3R catches up with its fully-supervised sibling models, taking a step towards low-cost 3D reconstruction supervisions and scalable FFRMs.

Keywords

Cite

@article{arxiv.2604.00548,
  title  = {Reliev3R: Relieving Feed-forward Reconstruction from Multi-View Geometric Annotations},
  author = {Youyu Chen and Junjun Jiang and Yueru Luo and Kui Jiang and Xianming Liu and Xu Yan and Dave Zhenyu Chen},
  journal= {arXiv preprint arXiv:2604.00548},
  year   = {2026}
}

Comments

Accepted by CVPR2026

R2 v1 2026-07-01T11:47:44.114Z