mlsanityData to 7 Oct 2026

MEt3R: Measuring Multi-View Consistency in Generated Images

arXiv 2501.06336 ↗First posted 10 Jan 2025cs.CV cs.LG eess.IVcited by 91

Not on the map. Why?

Cited by 30 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We introduce MEt3R, a metric for multi-view consistency in generated images. Large-scale generative models for multi-view image generation are rapidly advancing the field of 3D inference from sparse observations. However, due to the nature of generative modeling, traditional reconstruction metrics are not suitable to measure the quality of generated outputs and metrics that are independent of the sampling procedure are desperately needed. In this work, we specifically address the aspect of consistency between generated multi-view images, which can be evaluated independently of the specific scene. Our approach uses DUSt3R to obtain dense 3D reconstructions from image pairs in a feed-forward manner, which are used to warp image contents from one view into the other. Then, feature maps of these images are compared to obtain a similarity score that is invariant to view-dependent effects. Using MEt3R, we evaluate the consistency of a large set of previous methods for novel view and video generation, including our open, multi-view latent diffusion model.

Key facts. Cited by 91 papers in the map (data through 7 Oct 2026). Builds on 46 of its 53 references that are in the map. First posted on arXiv 10 Jan 2025.

Builds on

46 of 53 references.

References · 46

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  8. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  9. 2016Improved Techniques for Training GANscited by 2,938
  10. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  11. 2022Video Diffusion Modelscited by 2,280
  12. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,574
34 more
  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  2. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  3. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  4. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  5. 2018Demystifying MMD GANscited by 1,268
  6. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,204
  7. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  8. 2023MVDream: Multi-view Diffusion for 3D Generationcited by 928
  9. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
  10. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 638
  11. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  12. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 425
  13. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  14. 2023I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Modelscited by 343
  15. 2023ReconFusion: 3D Reconstruction with Diffusion Priorscited by 317
  16. 2023Rethinking FID: Towards a Better Evaluation Metric for Image Generationcited by 303
  17. 2022Novel View Synthesis with Diffusion Modelscited by 299
  18. 2023Generative Novel View Synthesis with 3D-Aware Diffusion Modelscited by 273
  19. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstructioncited by 216
  20. 2022DiffRF: Rendering-Guided 3D Radiance Field Diffusioncited by 204
  21. 2023Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstructioncited by 180
  22. 2024SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistencycited by 143
  23. 2022Open-Vocabulary Universal Image Segmentation with MaskCLIPcited by 131
  24. 2024FeatUp: A Model-Agnostic Framework for Features at Any Resolutioncited by 114
  25. 2024latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstructioncited by 114
  26. 2023Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervisioncited by 112
  27. 2021Geometry-Free View Synthesis: Transformers and no 3D Priorscited by 99
  28. 2023Long-Term Photometric Consistent Novel View Synthesis with Diffusion Modelscited by 76
  29. 2023EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusioncited by 72
  30. 2024GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warpingcited by 72
  31. 2024MultiDiff: Consistent Novel View Synthesis from a Single Imagecited by 67
  32. 2024VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Modelscited by 56
  33. 2024VideoMV: Consistent Multi-View Generation Based on Large Video Generative Modelcited by 45
  34. 2023Neural Point Cloud Diffusion for Disentangled 3D Shape and Appearance Generationcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 37; 2026: 54.

91 papers.

Sort:

By area:

  1. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 152
  2. 2025Reangle-A-Video: 4D Video Generation as Video-to-Video Translationcited by 35
  3. 2025AnyUp: Universal Feature Upsamplingcited by 26
  4. 2025Epipolar Geometry Improves Video Generation Modelscited by 22
  5. 2025Zero4D: Training-Free 4D Video Generation From Single Video Using Off-the-Shelf Video Diffusioncited by 15
  6. 2025EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memorycited by 14
  7. 2025SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steeringcited by 13
  8. 20253D Scene Prompting for Scene-Consistent Camera-Controllable Video Generationcited by 13
  9. 20254Real-Video-V2: Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generationcited by 12
  10. 2025Towards Cross-View Point Correspondence in Vision-Language Modelscited by 12
  11. 2026WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representationcited by 12
  12. 2026Repurposing Geometric Foundation Models for Multi-view Diffusioncited by 12
38 more
  1. 2025ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encodingcited by 10
  2. 2025MVGBench: Comprehensive Benchmark for Multi-view Generation Modelscited by 9
  3. 2026MV-S2V: Multi-View Subject-Consistent Video Generationcited by 9
  4. 2025SViM3D: Stable Video Material Diffusion for Single Image 3D Generationcited by 7
  5. 2025ByteLoom: Weaving Geometry-Consistent Human-Object Interactions through Progressive Curriculum Learningcited by 6
  6. 2026ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video Generationcited by 6
  7. 2026SceneTok: A Compressed, Diffusable Token Space for 3D Scenescited by 6
  8. 2025Bridging Diffusion Models and 3D Representations: A 3D Consistent Super-Resolution Frameworkcited by 5
  9. 2025CoreEditor: Correspondence-constrained Diffusion for Consistent 3D Editingcited by 5
  10. 2025Captain Safari: A World Engine with Pose-Aligned 3D Memorycited by 5
  11. 2026ArtiFixer: Enhancing and Extending 3D Reconstruction with Auto-Regressive Diffusion Modelscited by 5
  12. 2025Toward Stable World Models: Measuring and Addressing World Instability in Generative Environmentscited by 4
  13. 2025Coupled Diffusion Sampling for Training-Free Multi-View Image Editingcited by 4
  14. 2025Generative View Stitchingcited by 4
  15. 2025Appreciate the View: A Task-Aware Evaluation Framework for Novel View Synthesiscited by 4
  16. 2026VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative Alignmentcited by 4
  17. 2026SyncFix: Fixing 3D Reconstructions via Multi-View Synchronizationcited by 4
  18. 2026Pantheon360: Taming Digital Twin Generation via 3D-Aware 360deg Video Diffusioncited by 4
  19. 2025MeSS: City Mesh-Guided Outdoor Scene Generation with Cross-View Consistent Diffusioncited by 3
  20. 2025View-Consistent Diffusion Representations for 3D-Consistent Video Generationcited by 3
  21. 2025GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generationcited by 3
  22. 2025Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generationcited by 3
  23. 2026Quantitative Video World Model Evaluation for Geometric-Consistencycited by 3
  24. 2026BadWorld: Adversarial Attacks on World Modelscited by 3
  25. 2025DynamicEval: Rethinking Evaluation for Dynamic Text-to-Video Synthesiscited by 2
  26. 2025MVCustom: Multi-View Customized Diffusion via Geometric Latent Rendering and Completioncited by 2
  27. 2025Dynamic-eDiTor: Training-Free Text-Driven 4D Scene Editing with Multimodal Diffusion Transformercited by 2
  28. 2025ChronosObserver: Taming 4D World with Hyperspace Diffusion Samplingcited by 2
  29. 2025Splatent: Splatting Diffusion Latents for Novel View Synthesiscited by 2
  30. 2025StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Spacecited by 2
  31. 2026Geo-Align: Video Generation Alignment via Metric Geometry Rewardcited by 2
  32. 2026WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World Modelscited by 2
  33. 2026SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cuescited by 2
  34. 2026MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generationcited by 2
  35. 2026Faithfulness to Refusal: A Causal Audit of Neuron Selectorscited by 2
  36. 2025InstructMix2Mix: Consistent Sparse-View Editing Through Multi-View Model Personalizationcited by 1
  37. 20253D-Consistent Multi-View Editing by Correspondence Guidancecited by 1
  38. 2025GeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structurecited by 1

50 most cited of 91 All 91 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models
  2. 2023HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D
  3. 2023Consistent123: Improve Consistency for One Image to 3D Object Synthesis
  4. 2024MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model
  5. 2023ConsistNet: Enforcing 3D Consistency for Multi-view Images Diffusion
  6. 2024Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation
  7. 2024MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation
  8. 2025ConsistentDreamer: View-Consistent Meshes Through Balanced Multi-View Gaussian Optimization