awesome 3D Geometric Foundation Models and Application

3D Geometric Foundation Models

• DUSt3R: Geometric 3D Vision Made Easy, CVPR 2024. [Paper] [Code] [Website]
• Monst3r: A simple approach for estimating geometry in the presence of motion, arXiv 2024. [Paper] [Code] [Website]
• LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models, ICLR 2025. [Paper] [Website]
• (CUT3R) Continuous 3D Perception Model with Persistent State, arXiv 2025. [Paper] [Code] [Website]

Related Application

SLAM

• SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos, arXiv 2024. [Paper] [Code]
• MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors, arXiv 2024. [Paper] [Website] [Code todo]

Localization and Re-Localization:

• Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization, arXiv 2024. [Paper] [Code]

Scene Reconstruction

• DAS3R: Dynamics-Aware Gaussian Splatting for Static Scene Reconstruction, arXiv 2024. [Paper] [Code] [Website]
• MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion, arXiv 2024. [Paper]
• Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs, arXiv 2024. [Paper]
• SAB3R: Semantic-Augmented Backbone in 3D Reconstruction, arXiv 2024. [Paper]
• No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images, arXiv 2024. [Paper] [Code] [Website]
• Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features, arXiv 2024. [Paper]
• (Spann3R) 3D Reconstruction with Spatial Memory, 3DV 2025. [Paper] [Code] [Website]
• Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass, arXiv 2025. [Paper] [Website]

Depth Estimation

• Align3R: Aligned Monocular Depth Estimation for Dynamic Videos, arXiv 2024. [Paper] [Code] [Website]

Image Matching

• (MASt3R) Grounding Image Matching in 3D with MASt3R, ECCV 2024. [Paper] [Code] [Website]