MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details

TL;DR

MoGe-2 is a novel monocular geometry estimation model that accurately recovers metric scale 3D scenes with fine details from a single image, outperforming previous methods in accuracy and granularity.

Contribution

We extend the MoGe approach to predict metric geometry without losing relative accuracy and develop a data refinement method to enhance detail recovery from real data.

Findings

Achieves accurate metric scale in 3D reconstructions

Recovers fine-grained geometric details

Outperforms previous monocular geometry methods

Abstract

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.