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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Youyu, Jiang, Junjun, Luo, Yueru, Jiang, Kui, Liu, Xianming, Yan, Xu, Chen, Dave Zhenyu
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911559482081280
author Chen, Youyu
Jiang, Junjun
Luo, Yueru
Jiang, Kui
Liu, Xianming
Yan, Xu
Chen, Dave Zhenyu
author_facet Chen, Youyu
Jiang, Junjun
Luo, Yueru
Jiang, Kui
Liu, Xianming
Yan, Xu
Chen, Dave Zhenyu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2604_00548
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Reliev3R: Relieving Feed-forward Reconstruction from Multi-View Geometric Annotations
Chen, Youyu
Jiang, Junjun
Luo, Yueru
Jiang, Kui
Liu, Xianming
Yan, Xu
Chen, Dave Zhenyu
Computer Vision and Pattern Recognition
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.
title Reliev3R: Relieving Feed-forward Reconstruction from Multi-View Geometric Annotations
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.00548