mlsanityData to 7 Oct 2026

DUSt3R: Geometric 3D Vision Made Easy

arXiv 2312.14132 ↗First posted 21 Dec 2023cs.CVcited by 1,526

Not on the map. Why?

Cited by 122 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Multi-view stereo reconstruction (MVS) in the wild requires to first estimate the camera parameters e.g. intrinsic and extrinsic parameters. These are usually tedious and cumbersome to obtain, yet they are mandatory to triangulate corresponding pixels in 3D space, which is the core of all best performing MVS algorithms. In this work, we take an opposite stance and introduce DUSt3R, a radically novel paradigm for Dense and Unconstrained Stereo 3D Reconstruction of arbitrary image collections, i.e. operating without prior information about camera calibration nor viewpoint poses. We cast the pairwise reconstruction problem as a regression of pointmaps, relaxing the hard constraints of usual projective camera models. We show that this formulation smoothly unifies the monocular and binocular reconstruction cases. In the case where more than two images are provided, we further propose a simple yet effective global alignment strategy that expresses all pairwise pointmaps in a common reference frame. We base our network architecture on standard Transformer encoders and decoders, allowing us to leverage powerful pretrained models. Our formulation directly provides a 3D model of the scene as well as depth information, but interestingly, we can seamlessly recover from it, pixel matches, relative and absolute camera. Exhaustive experiments on all these tasks showcase that the proposed DUSt3R can unify various 3D vision tasks and set new SoTAs on monocular/multi-view depth estimation as well as relative pose estimation. In summary, DUSt3R makes many geometric 3D vision tasks easy.

Key facts. Cited by 1,526 papers in the map (data through 7 Oct 2026). Builds on 135 of its 196 references that are in the map. First posted on arXiv 21 Dec 2023.

Builds on

135 of 196 references.

References · 135

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  6. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  7. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  8. 2021Vision Transformers for Dense Predictioncited by 1,789
  9. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
  10. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
  11. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  12. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
38 more
  1. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  2. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,230
  3. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  4. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  5. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  6. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  7. 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 862
  8. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  9. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  10. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  11. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  12. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
  13. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  14. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
  15. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  16. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  17. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  18. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 641
  19. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
  20. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  21. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
  22. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 556
  23. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 487
  24. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  25. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 437
  26. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 414
  27. 2019SynSin: End-to-end View Synthesis from a Single Imagecited by 364
  28. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  29. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  30. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 324
  31. 2020DISK: Learning local features with policy gradientcited by 310
  32. 2020Learning to Explore using Active Neural SLAMcited by 308
  33. 2016LIFT: Learned Invariant Feature Transformcited by 305
  34. 2023RoMa: Robust Dense Feature Matchingcited by 296
  35. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 264
  36. 2019What Do Single-view 3D Reconstruction Networks Learn?cited by 259
  37. 2018Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationcited by 222
  38. 2020Learning to Recover 3D Scene Shape from a Single Imagecited by 214

50 most cited of 135 All 135 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 174; 2025: 628; 2026: 724.

1,526 papers.

Sort:

By area:

  1. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  2. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  3. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  4. 2025Continuous 3D Perception Model with Persistent Statecited by 527
  5. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 431
  6. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 392
  7. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 356
  8. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
  9. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 325
  10. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 295
  11. 2025π3: Permutation-Equivariant Visual Geometry Learningcited by 292
  12. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 290
38 more
  1. 20243D Reconstruction with Spatial Memorycited by 269
  2. 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 250
  3. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 247
  4. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 241
  5. 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 234
  6. 2024MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videoscited by 224
  7. 20243D Gaussian Splatting as Markov Chain Monte Carlocited by 210
  8. 2025Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligencecited by 206
  9. 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 198
  10. 2025Stable Virtual Camera: Generative View Synthesis with Diffusion Modelscited by 179
  11. 2024LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awarenesscited by 178
  12. 2024MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffoldscited by 177
  13. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 176
  14. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 171
  15. 2025FoundationStereo: Zero-Shot Stereo Matchingcited by 168
  16. 2025ViPE: Video Pose Engine for 3D Geometric Perceptioncited by 162
  17. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 161
  18. 2025VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstructioncited by 154
  19. 2025WorldMem: Long-term Consistent World Simulation with Memorycited by 152
  20. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 152
  21. 2024AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformerscited by 151
  22. 2025Streaming 4D Visual Geometry Transformercited by 147
  23. 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Modelcited by 139
  24. 2024DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusioncited by 139
  25. 2025MUSt3R: Multi-view Network for Stereo 3D Reconstructioncited by 139
  26. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 138
  27. 2024MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Secondscited by 136
  28. 2025VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifoldcited by 130
  29. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 129
  30. 2025Video World Models with Long-term Spatial Memorycited by 124
  31. 2025TTT3R: 3D Reconstruction as Test-Time Trainingcited by 122
  32. 2025TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Modelscited by 120
  33. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 113
  34. 2025Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priorscited by 111
  35. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 108
  36. 2025VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequencescited by 107
  37. 2025VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memorycited by 102
  38. 2024SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videoscited by 100

50 most cited of 1,526 All 1,526 (JSON)