mlsanityData to 14 Oct 2026

Depth Anything 3: Recovering the Visual Space from Any Views

arXiv 2511.10647 ↗First posted 13 Nov 2025cs.CVcited by 692

Not on the map. Why?

Cited by 83 in World models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present Depth Anything 3 (DA3), a model that predicts spatially consistent geometry from an arbitrary number of visual inputs, with or without known camera poses. In pursuit of minimal modeling, DA3 yields two key insights: a single plain transformer (e.g., vanilla DINO encoder) is sufficient as a backbone without architectural specialization, and a singular depth-ray prediction target obviates the need for complex multi-task learning. Through our teacher-student training paradigm, the model achieves a level of detail and generalization on par with Depth Anything 2 (DA2). We establish a new visual geometry benchmark covering camera pose estimation, any-view geometry and visual rendering. On this benchmark, DA3 sets a new state-of-the-art across all tasks, surpassing prior SOTA VGGT by an average of 44.3% in camera pose accuracy and 25.1% in geometric accuracy. Moreover, it outperforms DA2 in monocular depth estimation. All models are trained exclusively on public academic datasets.

Key facts. Cited by 692 papers in the map (data through 14 Oct 2026). Builds on 91 of its 119 references that are in the map. First posted on arXiv 13 Nov 2025.

Builds on

91 of 119 references.

References · 91

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  3. 2022Scalable Diffusion Models with Transformerscited by 6,054
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  5. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  6. 2021Vision Transformers for Dense Predictioncited by 1,803
  7. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  8. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  9. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  10. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  11. 2024Depth Anything V2cited by 1,422
  12. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
38 more
  1. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  2. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 988
  3. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  4. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 904
  5. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  6. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  7. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  8. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 770
  9. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  10. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  11. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  12. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 707
  13. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 684
  14. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  15. 2018Taskonomy: Disentangling Task Transfer Learningcited by 634
  16. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 616
  17. 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 604
  18. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 566
  19. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  20. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 537
  21. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 506
  22. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  23. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 454
  24. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
  25. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 439
  26. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 404
  27. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 395
  28. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 382
  29. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 367
  30. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 365
  31. 2021Light Field Networks: Neural Scene Representations with Single-Evaluation Renderingcited by 332
  32. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 327
  33. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 326
  34. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 326
  35. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 314
  36. 2021DSEC: A Stereo Event Camera Dataset for Driving Scenarioscited by 303
  37. 2024MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervisioncited by 299
  38. 2019Structured3D: A Large Photo-realistic Dataset for Structured 3D Modelingcited by 286

50 most cited of 91 All 91 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 16; 2026: 676.

692 papers.

Sort:

By area:

  1. 2026Cosmos 3: Omnimodal World Models for Physical AIcited by 165
  2. 2026Advancing Open-source World Modelscited by 154
  3. 2026Unified 4D World Action Modeling from Video Priors with Asynchronous Denoisingcited by 71
  4. 2025RoMa v2: Harder Better Faster Denser Feature Matchingcited by 51
  5. 2026Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Modelscited by 50
  6. 2026NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videoscited by 46
  7. 2026Lyra 2.0: Explorable Generative 3D Worldscited by 44
  8. 2026HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worldscited by 44
  9. 2026Image Generators are Generalist Vision Learnerscited by 43
  10. 2026WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluationcited by 39
  11. 2026LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstructioncited by 37
  12. 2026LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Modelscited by 28
38 more
  1. 2026MosaicMem: Hybrid Spatial Memory for Controllable Video World Modelscited by 27
  2. 2026WorldMark: A Unified Benchmark Suite for Interactive Video World Modelscited by 26
  3. 2026VGGT-Omegacited by 26
  4. 2026WorldCompass: Reinforcement Learning for Long-Horizon World Modelscited by 24
  5. 2026VGGRPO: Towards World-Consistent Video Generation with 4D Latent Rewardcited by 24
  6. 2026VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generationcited by 23
  7. 20264RC: 4D Reconstruction via Conditional Querying Anytime and Anywherecited by 22
  8. 2026Utonia: Toward One Encoder for All Point Cloudscited by 21
  9. 2026DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Modelscited by 20
  10. 2025RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstructioncited by 19
  11. 2026MV-SAM3D: Adaptive Multi-View Fusion for Layout-Aware 3D Generationcited by 19
  12. 2026MBench: A Comprehensive Benchmark on Memory Capability for Video World Modelscited by 18
  13. 2026MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulationcited by 17
  14. 2026S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresightcited by 17
  15. 2026DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planningcited by 17
  16. 2026Latent Spatial Memory for Video World Modelscited by 17
  17. 2026SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoningcited by 17
  18. 2026Hand2World: Autoregressive Egocentric Interaction Generation via Free-Space Hand Gesturescited by 16
  19. 2026Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Modelcited by 16
  20. 2026Repurposing Geometric Foundation Models for Multi-view Diffusioncited by 15
  21. 2026EponaV2: Driving World Model with Comprehensive Future Reasoningcited by 15
  22. 2026WAM4D: Fast 4D World Action Model via Spatial Register Tokenscited by 15
  23. 2026Wonder: Video World Model Done Bettercited by 15
  24. 2026EgoSim: Egocentric World Simulator for Embodied Interaction Generationcited by 14
  25. 2026Video Generation Models are General-Purpose Vision Learnerscited by 14
  26. 2026Alaya-EVOKE: From Linear-Scaling Supervision to Endless Worldcited by 14
  27. 2026Any3D-VLA: Enhancing VLA Robustness via Diverse Point Cloudscited by 13
  28. 2026Track4World: Feedforward World-centric Dense 3D Tracking of All Pixelscited by 13
  29. 2026Geometry-Aware Implicit Memory for Video World Modelscited by 13
  30. 2026Grounding World Simulation Models in a Real-World Metropoliscited by 12
  31. 2026GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokenscited by 12
  32. 2026CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Drivingcited by 12
  33. 2025Off The Grid: Detection of Primitives for Feed-Forward 3D Gaussian Splattingcited by 11
  34. 2026ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Modelscited by 11
  35. 2026Uni-World VLA: Interleaved World Modeling and Planning for Autonomous Drivingcited by 11
  36. 2026NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Resultscited by 11
  37. 2026LoMa: Local Feature Matching Revisitedcited by 11
  38. 2026World-R1: Reinforcing 3D Constraints for Text-to-Video Generationcited by 11

50 most cited of 692 All 692 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Anything-3D: Towards Single-view Anything Reconstruction in the Wild
  2. 2025UniK3D: Universal Camera Monocular 3D Estimation
  3. 2023ADU-Depth: Attention-based Distillation with Uncertainty Modeling for Depth Estimation
  4. 2022Depth Field Networks for Generalizable Multi-view Scene Representation
  5. 2023Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models
  6. 2026ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device
  7. 2026CAM3R: Camera-Agnostic Model for 3D Reconstruction
  8. 2026Speed3R: Sparse Feed-forward 3D Reconstruction Models