Awesome-DUST3R🔥

A curated list of awesome DUST3R/MAST3R related papers.

Table of Contents

• Originals
• Related Works
• Papers
  

Originals

• DUSt3R: Geometric 3D Vision Made Easy (CVPR 2024) [paper] [code] [project page]
• Grounding Image Matching in 3D with MASt3R (ECCV 2024) [paper] [code] [project page]
• MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion (arXiv 2024) [paper] [code]
  

Related Works

• CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion (NeurIPS 2022) [paper] [code] [project page]
• CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow (ICCV 2023) [paper] [code] [project page]
  

Papers

2025

• GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors (ICCV 2025) [paper] [code] [project page]

• PanSt3R: Multi-view Consistent Panoptic Segmentation (ICCV 2025) [paper]

• Easi3R: Estimating Disentangled Motion from DUSt3R Without Training (ICCV 2025) [paper] [code] [project page]

• Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars (ICCV 2025) [paper] [project page]

• PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction (ICCV 2025) [paper] [code] [project page]

• LONG3R: Long Sequence Streaming 3D Reconstruction (ICCV 2025) [paper] [code] [project page]

• Image as an IMU: Estimating Camera Motion from a Single Motion-Blurred Image (ICCV 2025 Oral) [paper] [project page]

  
  

• SAB3R: Semantic-Augmented Backbone in 3D Reconstruction (CVPR 2025 Workshop)[paper] [project page]

• FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views (CVPR 2025) [paper] [code] [project page]

• Reconstructing People, Places, and Cameras (CVPR 2025) [paper] [code] [project page]

• MVSAnywhere: Zero-Shot Multi-View Stereo (CVPR 2025) [paper] [project page]

• Free360: Layered Gaussian Splatting for Unbounded 360-Degree View Synthesis from Extremely Sparse and Unposed Views (CVPR 2025) [paper] [code] [project page]

• DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers (CVPR 2025) [paper] [code] [project page]

• Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors (CVPR 2025) [paper] [code] [project page]

• CoMatcher: Multi-View Collaborative Feature Matching (CVPR 2025) [paper]

• MUSt3R: Multi-view Network for Stereo 3D Reconstruction (CVPR 2025) [paper] [code]

• Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass (CVPR 2025) [paper] [code] [project page]

• MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds (CVPR 2025) [paper] [code] [project page]

• Align3R: Aligned Monocular Depth Estimation for Dynamic Videos (CVPR 2025) [paper] [code] [project page]

• SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos (CVPR 2025) [paper] [code]

• Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization (CVPR 2025) [paper] [code]

• MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors (CVPR 2025) [paper] [code] [project page]

• MEt3R: Measuring Multi-View Consistency in Generated Images (CVPR 2025) [paper] [code] [project page]

• Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features (CVPR 2025 Highlight) [paper] [code] [project page]

• Can Generative Video Models Help Pose Estimation? (CVPR 2025 Highlight) [paper] [project page]

• Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputs (CVPR 2025 Highlight) [paper] [code] [project page]

• MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos (CVPR 2025 Oral) [paper] [code] [project page]

• Continuous 3D Perception Model with Persistent State (CUT3R) (CVPR 2025 Oral) [paper] [code] [project page]

• Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos (CVPR 2025 Oral) [paper] [project page]

• VGGT: Visual Geometry Grounded Transformer (CVPR 2025 Best Paper Award) [paper] [code] [project page]

  
  

• GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting (ICLR 2025) [paper] [code] [project page]

• Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model (ICLR 2025) [paper] [code]

• LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models (ICLR 2025 Spotlight) [paper]

• MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion (ICLR 2025 Spotlight) [paper] [code] [project page]

• No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images (ICLR 2025 Oral) [paper] [code] [project page]

  
  

• 3D Reconstruction with Spatial Memory (3DV 2025) [paper] [code] [project page]

  
  

• GFlow: Recovering 4D World from Monocular Video (AAAI 2025) [paper] [code] [project page]

  
  

• Alligat0R: Pre-Training Through Co-Visibility Segmentation for Relative Camera Pose Regression (arXiv 2025) [paper]

• D^2USt3R: Enhancing 3D Reconstruction with 4D Pointmaps for Dynamic Scenes (arXiv 2025) [paper] [code] [project page]

  
  

2024

• Large Spatial Model: End-to-end Unposed Images to Semantic 3D (NeurIPS 2024) [paper] [code] [project page]

• From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos (NeurIPS 2024) [paper] [code] [project page]

  
  

• PreF3R: Pose-Free Feed-Forward 3D Gaussian Splatting from Variable-length Image Sequence (arXiv 2024) [paper] [project page]

• Dense Point Clouds Matter: Dust-GS for Scene Reconstruction from Sparse Viewpoints (arXiv 2024) [paper]

• InstantSplat: Sparse-view SfM-free Gaussian Splatting in Seconds (arXiv 2024) [paper] [code] [project page]

• Improving Geometry in Sparse-View 3DGS via Reprojection-based DoF Separation (arXiv 2024) [paper]

• LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors (arXiv 2024) [paper] [code] [project page]

• Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs (arXiv 2024) [paper] [code] [project page]

• Mutli-View 3D Reconstruction using Knowledge Distillation (arXiv 2024) [paper]

• Driv3R: Learning Dense 4D Reconstruction for Autonomous Driving (arXiv 2024) [paper] [code]

• VI3DRM:Towards meticulous 3D Reconstruction from Sparse Views via Photo-Realistic Novel View Synthesis (arXiv 2024) [paper]

• PhotoReg: Photometrically Registering 3D Gaussian Splatting Models (arXiv 2024) [paper] [code] [project page]

• ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis (arXiv 2025) [paper] [code] [project page]