mlsanityData to 14 Oct 2026

MVImgNet: A Large-scale Dataset of Multi-view Images

arXiv 2303.06042 ↗First posted 10 Mar 2023cs.CVcited by 220

Not on the map. Why?

Cited by 59 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Being data-driven is one of the most iconic properties of deep learning algorithms. The birth of ImageNet drives a remarkable trend of "learning from large-scale data" in computer vision. Pretraining on ImageNet to obtain rich universal representations has been manifested to benefit various 2D visual tasks, and becomes a standard in 2D vision. However, due to the laborious collection of real-world 3D data, there is yet no generic dataset serving as a counterpart of ImageNet in 3D vision, thus how such a dataset can impact the 3D community is unraveled. To remedy this defect, we introduce MVImgNet, a large-scale dataset of multi-view images, which is highly convenient to gain by shooting videos of real-world objects in human daily life. It contains 6.5 million frames from 219,188 videos crossing objects from 238 classes, with rich annotations of object masks, camera parameters, and point clouds. The multi-view attribute endows our dataset with 3D-aware signals, making it a soft bridge between 2D and 3D vision. We conduct pilot studies for probing the potential of MVImgNet on a variety of 3D and 2D visual tasks, including radiance field reconstruction, multi-view stereo, and view-consistent image understanding, where MVImgNet demonstrates promising performance, remaining lots of possibilities for future explorations. Besides, via dense reconstruction on MVImgNet, a 3D object point cloud dataset is derived, called MVPNet, covering 87,200 samples from 150 categories, with the class label on each point cloud. Experiments show that MVPNet can benefit the real-world 3D object classification while posing new challenges to point cloud understanding. MVImgNet and MVPNet will be publicly available, hoping to inspire the broader vision community.

Key facts. Cited by 220 papers in the map (data through 14 Oct 2026). Builds on 76 of its 123 references that are in the map. First posted on arXiv 10 Mar 2023.

Builds on

76 of 123 references.

References · 76

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2017Mask R-CNNcited by 7,277
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  8. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  9. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  10. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  11. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  12. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
38 more
  1. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  5. 2015Fast R-CNNcited by 2,933
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  7. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  8. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  9. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  10. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  11. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  12. 2017The Kinetics Human Action Video Datasetcited by 1,909
  13. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  14. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,616
  15. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  16. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  17. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  18. 2019HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clipscited by 950
  19. 2020Pre-Trained Image Processing Transformercited by 893
  20. 2017Dense-Captioning Events in Videoscited by 793
  21. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  22. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  23. 2020PCT: Point cloud transformercited by 732
  24. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
  25. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  26. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  27. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  28. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 612
  29. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  30. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  31. 2020U2-Net: Going Deeper with Nested U-Structure for Salient Object Detectioncited by 412
  32. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 405
  33. 20203D-FRONT: 3D Furnished Rooms with layOuts and semaNTicscited by 380
  34. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  35. 2018Rethinking ImageNet Pre-trainingcited by 377
  36. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 366
  37. 2018ABC: A Big CAD Model Dataset For Geometric Deep Learningcited by 341
  38. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 254

50 most cited of 76 All 76 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 26; 2024: 94; 2025: 73; 2026: 27.

220 papers.

Sort:

By area:

  1. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  2. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  3. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 537
  4. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 460
  5. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 432
  6. 2023AnyDoor: Zero-shot Object-level Image Customizationcited by 412
  7. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 403
  8. 2023ReconFusion: 3D Reconstruction with Diffusion Priorscited by 318
  9. 2024AnyEdit: Mastering Unified High-Quality Image Editing for Any Ideacited by 241
  10. 2023DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Modelcited by 214
  11. 2023DreamGaussian4D: Generative 4D Gaussian Splattingcited by 194
  12. 2023RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3Dcited by 168
38 more
  1. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  2. 2024CAT4D: Create Anything in 4D with Multi-View Video Diffusion Modelscited by 161
  3. 2025Less-to-More Generalization: Unlocking More Controllability by In-Context Generationcited by 154
  4. 2024Training-free Camera Control for Video Generationcited by 122
  5. 20234DGen: Grounded 4D Content Generation with Spatial-temporal Consistencycited by 117
  6. 2024MV-Adapter: Multi-view Consistent Image Generation Made Easycited by 112
  7. 2024MeshXL: Neural Coordinate Field for Generative 3D Foundation Modelscited by 103
  8. 2024GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creationcited by 100
  9. 2025Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridgingcited by 99
  10. 2024LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generationcited by 92
  11. 2024V3D: Video Diffusion Models are Effective 3D Generatorscited by 89
  12. 2024Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splattingcited by 82
  13. 2025SpatialVID: A Large-Scale Video Dataset with Spatial Annotationscited by 77
  14. 2024InstantSplat: Sparse-view Gaussian Splatting in Secondscited by 70
  15. 2024Controlling Space and Time with Diffusion Modelscited by 66
  16. 2024World-consistent Video Diffusion with Explicit 3D Modelingcited by 65
  17. 2024You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scalecited by 65
  18. 2025DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learningcited by 65
  19. 2024IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representationcited by 64
  20. 2024Advances in 3D Generation: A Surveycited by 63
  21. 2023Generative AI meets 3D: A Survey on Text-to-3D in AIGC Eracited by 61
  22. 2025Insert Anything: Image Insertion via In-Context Editing in DiTcited by 61
  23. 2025Bolt3D: Generating 3D Scenes in Secondscited by 59
  24. 2024MegaScenes: Scene-Level View Synthesis at Scalecited by 58
  25. 2024VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Modelscited by 56
  26. 2024Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstructioncited by 56
  27. 2024Animate3D: Animating Any 3D Model with Multi-view Video Diffusioncited by 56
  28. 2024IDOL: Instant Photorealistic 3D Human Creation from a Single Imagecited by 55
  29. 2023MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Capturescited by 54
  30. 2023NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotationscited by 53
  31. 2024AGG: Amortized Generative 3D Gaussians for Single Image to 3Dcited by 53
  32. 2023AutoDecoding Latent 3D Diffusion Modelscited by 50
  33. 2024Director3D: Real-world Camera Trajectory and 3D Scene Generation from Textcited by 50
  34. 2024GenXD: Generating Any 3D and 4D Scenescited by 50
  35. 2024Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videoscited by 49
  36. 2024Human-3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Modelscited by 44
  37. 2025VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Controlcited by 42
  38. 2024FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstructioncited by 41

50 most cited of 220 All 220 (JSON)