UniMetric: Universal Metric Scale Recovery for Visual Geometry Foundation Models

arXiv:2610.16945 · cs.CV · Submitted 2026-10-12 · Read on arXiv

cs.CV

Submitted: 2026-10-12

Updated: 2026-10-12

Comments: 39 pages. Technical report. Code: https://github.com/yanglei18/UniMetric ; Data: https://huggingface.co/datasets/yanglei18/MetricBench

Code: https://github.com/yanglei18/UniMetric

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes

Sources

• ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth
• D'ej\`a View: Looping Transformers for Multi-View 3D Reconstruction
• Seed1.8 Model Card: Towards Generalized Real-World Agency
• In-Context Robot Learning with VLM Agents
• MapAnything: Universal Feed-Forward Metric 3D Reconstruction
• VIDAR: Visual-Inertial Dense Alignment and Reconstruction via a Geometric Foundation Model
• VGGT-$\Omega$
• Humanoid Everyday: A Comprehensive Robotic Dataset for Open-World Humanoid Manipulation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models