DGSfM: Depth-Guided Scale-Aware Global Structure-from-Motion

arXiv:2607.09507 · cs.CV · Submitted 2026-07-10 · Read on arXiv

cs.CV

Submitted: 2026-07-10

Updated: 2026-10-12

Code: https://github.com/sithu31296/DGSfM

Terminology

• Global Structure-from-Motion — 2× in this paper
• Accuracy — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• Distributed Global Structure-from-Motion with a Deep Front-End
• MiDaS v3.1 -- A Model Zoo for Robust Monocular Relative Depth Estimation
• VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequences
• RoMa v2: Harder Better Faster Denser Feature Matching
• Depth Anything 3: Recovering the Visual Space from Any Views
• Benchmarking Efficient & Effective Camera Pose Estimation Strategies for Novel View Synthesis
• LoMa: Local Feature Matching Revisited
• UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler
• VGGT-$\Omega$
• MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details
• $\pi^3$: Permutation-Equivariant Visual Geometry Learning
• Depth Anything V2
• Bundle Adjustment in the Eager Mode
• UFM: A Simple Path towards Unified Dense Correspondence with Flow

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