mlsanityData to 7 Oct 2026

ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes

arXiv 1702.04405 ↗First posted 14 Feb 2017cs.CVcited by 3,088

Not on the map. Why?

Cited by 197 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

A key requirement for leveraging supervised deep learning methods is the availability of large, labeled datasets. Unfortunately, in the context of RGB-D scene understanding, very little data is available -- current datasets cover a small range of scene views and have limited semantic annotations. To address this issue, we introduce ScanNet, an RGB-D video dataset containing 2.5M views in 1513 scenes annotated with 3D camera poses, surface reconstructions, and semantic segmentations. To collect this data, we designed an easy-to-use and scalable RGB-D capture system that includes automated surface reconstruction and crowdsourced semantic annotation. We show that using this data helps achieve state-of-the-art performance on several 3D scene understanding tasks, including 3D object classification, semantic voxel labeling, and CAD model retrieval. The dataset is freely available at http://www.scan-net.org.

Key facts. Cited by 3,088 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Feb 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 254; 2022: 369; 2023: 530; 2024: 617; 2025: 713; 2026: 605.

3,088 papers.

Sort:

By area:

  1. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,669
  2. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  3. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,522
  4. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  5. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  6. 2025Qwen-Image Technical Reportcited by 973
  7. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 770
  8. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
  9. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  10. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  11. 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spacescited by 580
  12. 2021Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AIcited by 579
38 more
  1. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
  2. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  3. 2022OpenScene: 3D Scene Understanding with Open Vocabulariescited by 556
  4. 2023Otter: A Multi-Modal Model with In-Context Instruction Tuningcited by 548
  5. 2023LERF: Language Embedded Radiance Fieldscited by 538
  6. 2025Continuous 3D Perception Model with Persistent Statecited by 527
  7. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 514
  8. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  9. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  10. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 442
  11. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  12. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 431
  13. 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 411
  14. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 395
  15. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 392
  16. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  17. 2023Gaussian Grouping: Segment and Edit Anything in 3D Scenescited by 387
  18. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 386
  19. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
  20. 2024UniDepth: Universal Monocular Metric Depth Estimationcited by 375
  21. 2022Kubric: A scalable dataset generatorcited by 373
  22. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
  23. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  24. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 356
  25. 2023An Embodied Generalist Agent in 3D Worldcited by 355
  26. 2021ScanQA: 3D Question Answering for Spatial Scene Understandingcited by 340
  27. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  28. 2023PointLLM: Empowering Large Language Models to Understand Point Cloudscited by 326
  29. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 325
  30. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 323
  31. 20243D-VLA: A 3D Vision-Language-Action Generative World Modelcited by 320
  32. 2021Neural RGB-D Surface Reconstructioncited by 312
  33. 2022SQA3D: Situated Question Answering in 3D Scenescited by 303
  34. 2023ConceptFusion: Open-set Multimodal 3D Mappingcited by 302
  35. 2021Dense Depth Priors for Neural Radiance Fields from Sparse Input Viewscited by 301
  36. 2022Mask3D: Mask Transformer for 3D Semantic Instance Segmentationcited by 299
  37. 2023RoMa: Robust Dense Feature Matchingcited by 296
  38. 2025π3: Permutation-Equivariant Visual Geometry Learningcited by 292

50 most cited of 3,088 All 3,088 (JSON)