mlsanityData to 14 Oct 2026

DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision

arXiv 2312.16256 ↗First posted 26 Dec 2023cs.CV cs.AIcited by 537

Not on the map. Why?

Cited by 112 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS). However, existing scene-level datasets for deep learning-based 3D vision, limited to either synthetic environments or a narrow selection of real-world scenes, are quite insufficient. This insufficiency not only hinders a comprehensive benchmark of existing methods but also caps what could be explored in deep learning-based 3D analysis. To address this critical gap, we present DL3DV-10K, a large-scale scene dataset, featuring 51.2 million frames from 10,510 videos captured from 65 types of point-of-interest (POI) locations, covering both bounded and unbounded scenes, with different levels of reflection, transparency, and lighting. We conducted a comprehensive benchmark of recent NVS methods on DL3DV-10K, which revealed valuable insights for future research in NVS. In addition, we have obtained encouraging results in a pilot study to learn generalizable NeRF from DL3DV-10K, which manifests the necessity of a large-scale scene-level dataset to forge a path toward a foundation model for learning 3D representation. Our DL3DV-10K dataset, benchmark results, and models will be publicly accessible at https://dl3dv-10k.github.io/DL3DV-10K/.

Key facts. Cited by 537 papers in the map (data through 14 Oct 2026). Builds on 35 of its 49 references that are in the map. First posted on arXiv 26 Dec 2023.

Builds on

35 of 49 references.

References · 35

  1. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  2. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  5. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  6. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  7. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  8. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  9. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  10. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  11. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  12. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
23 more
  1. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  2. 2019Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelinescited by 672
  3. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  4. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  5. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 600
  6. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  7. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  8. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 454
  9. 2018DeepVoxels: Learning Persistent 3D Feature Embeddingscited by 405
  10. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 336
  11. 2023MVImgNet: A Large-scale Dataset of Multi-view Imagescited by 220
  12. 2021Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenescited by 190
  13. 2020GRF: Learning a General Radiance Field for 3D Representation and Renderingcited by 183
  14. 2020Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotationscited by 155
  15. 2021ShaRF: Shape-conditioned Radiance Fields from a Single Viewcited by 92
  16. 2020Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Imagescited by 79
  17. 2016Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networkscited by 35
  18. 2020SSN: Soft Shadow Network for Image Compositingcited by 26
  19. 2022Controllable Shadow Generation Using Pixel Height Mapscited by 22
  20. 2022Generalizable Neural Radiance Fields for Novel View Synthesis with Transformercited by 21
  21. 2023PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositingcited by 15
  22. 2015Deep Reflectance Mapscited by 13
  23. 2020Design and Deployment of Photo2Building: A Cloud-based Procedural Modeling Tool as a Servicecited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 48; 2025: 179; 2026: 310.

537 papers.

Sort:

By area:

  1. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  2. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 692
  3. 2025Continuous 3D Perception Model with Persistent Statecited by 548
  4. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 403
  5. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 341
  6. 2025MapAnything: Universal Feed-Forward Metric 3D Reconstructioncited by 314
  7. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 286
  8. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 248
  9. 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 243
  10. 2025Stable Virtual Camera: Generative View Synthesis with Diffusion Modelscited by 182
  11. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 180
  12. 2025UniDepthV2: Universal Monocular Metric Depth Estimation Made Simplercited by 173
38 more
  1. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 170
  2. 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Modelscited by 161
  3. 2024ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Modelcited by 143
  4. 2024MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Secondscited by 141
  5. 2025MUSt3R: Multi-view Network for Stereo 3D Reconstructioncited by 141
  6. 2024DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusioncited by 140
  7. 2025Test-Time Training Done Rightcited by 130
  8. 2025TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Modelscited by 125
  9. 2025Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noisecited by 117
  10. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 116
  11. 2024Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splatscited by 114
  12. 20243DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priorscited by 106
  13. 2025Cameras as Relative Positional Encodingcited by 105
  14. 2026Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memorycited by 100
  15. 2024Wonderland: Navigating 3D Scenes from a Single Imagecited by 99
  16. 2025CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Modelscited by 98
  17. 2025Controllable Video Generation: A Surveycited by 98
  18. 2025SpatialTrackerV2: 3D Point Tracking Made Easycited by 87
  19. 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 82
  20. 2025STream3R: Scalable Sequential 3D Reconstruction with Causal Transformercited by 82
  21. 2025Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generationcited by 77
  22. 2025RayZer: A Self-supervised Large View Synthesis Modelcited by 77
  23. 2025SpatialVID: A Large-Scale Video Dataset with Spatial Annotationscited by 77
  24. 2024InstantSplat: Sparse-view Gaussian Splatting in Secondscited by 70
  25. 2025Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generationcited by 67
  26. 2025WorldMirror: Universal 3D World Reconstruction with Any-Prior Promptingcited by 67
  27. 2024You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scalecited by 65
  28. 2025Towards Understanding Camera Motions in Any Videocited by 64
  29. 2024PF3plat: Pose-Free Feed-Forward 3D Gaussian Splattingcited by 62
  30. 2025UniK3D: Universal Camera Monocular 3D Estimationcited by 62
  31. 2025OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modelingcited by 62
  32. 2025Bolt3D: Generating 3D Scenes in Secondscited by 59
  33. 2024MegaScenes: Scene-Level View Synthesis at Scalecited by 58
  34. 2025DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Modelscited by 57
  35. 2026SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformercited by 55
  36. 2024Fast Feedforward 3D Gaussian Splatting Compressioncited by 52
  37. 2024Director3D: Real-world Camera Trajectory and 3D Scene Generation from Textcited by 50
  38. 2025MindJourney: Test-Time Scaling with World Models for Spatial Reasoningcited by 50

50 most cited of 537 All 537 (JSON)