Saved in:
Bibliographic Details
Main Authors: Wang, Ruicheng, Xu, Sicheng, Dong, Yue, Deng, Yu, Xiang, Jianfeng, Lv, Zelong, Sun, Guangzhong, Tong, Xin, Yang, Jiaolong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.02546
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911036609658880
author Wang, Ruicheng
Xu, Sicheng
Dong, Yue
Deng, Yu
Xiang, Jianfeng
Lv, Zelong
Sun, Guangzhong
Tong, Xin
Yang, Jiaolong
author_facet Wang, Ruicheng
Xu, Sicheng
Dong, Yue
Deng, Yu
Xiang, Jianfeng
Lv, Zelong
Sun, Guangzhong
Tong, Xin
Yang, Jiaolong
contents We propose MoGe-2, an advanced open-domain geometry estimation model that recovers a metric scale 3D point map of a scene from a single image. Our method builds upon the recent monocular geometry estimation approach, MoGe, which predicts affine-invariant point maps with unknown scales. We explore effective strategies to extend MoGe for metric geometry prediction without compromising the relative geometry accuracy provided by the affine-invariant point representation. Additionally, we discover that noise and errors in real data diminish fine-grained detail in the predicted geometry. We address this by developing a unified data refinement approach that filters and completes real data from different sources using sharp synthetic labels, significantly enhancing the granularity of the reconstructed geometry while maintaining the overall accuracy. We train our model on a large corpus of mixed datasets and conducted comprehensive evaluations, demonstrating its superior performance in achieving accurate relative geometry, precise metric scale, and fine-grained detail recovery -- capabilities that no previous methods have simultaneously achieved.
format Preprint
id arxiv_https___arxiv_org_abs_2507_02546
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details
Wang, Ruicheng
Xu, Sicheng
Dong, Yue
Deng, Yu
Xiang, Jianfeng
Lv, Zelong
Sun, Guangzhong
Tong, Xin
Yang, Jiaolong
Computer Vision and Pattern Recognition
We propose MoGe-2, an advanced open-domain geometry estimation model that recovers a metric scale 3D point map of a scene from a single image. Our method builds upon the recent monocular geometry estimation approach, MoGe, which predicts affine-invariant point maps with unknown scales. We explore effective strategies to extend MoGe for metric geometry prediction without compromising the relative geometry accuracy provided by the affine-invariant point representation. Additionally, we discover that noise and errors in real data diminish fine-grained detail in the predicted geometry. We address this by developing a unified data refinement approach that filters and completes real data from different sources using sharp synthetic labels, significantly enhancing the granularity of the reconstructed geometry while maintaining the overall accuracy. We train our model on a large corpus of mixed datasets and conducted comprehensive evaluations, demonstrating its superior performance in achieving accurate relative geometry, precise metric scale, and fine-grained detail recovery -- capabilities that no previous methods have simultaneously achieved.
title MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.02546