mlsanityData to 14 Oct 2026

LABELMAKER: Automatic Semantic Label Generation from RGB-D Trajectories

arXiv 2311.12174 ↗First posted 20 Nov 2023cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

Semantic annotations are indispensable to train or evaluate perception models, yet very costly to acquire. This work introduces a fully automated 2D/3D labeling framework that, without any human intervention, can generate labels for RGB-D scans at equal (or better) level of accuracy than comparable manually annotated datasets such as ScanNet. Our approach is based on an ensemble of state-of-the-art segmentation models and 3D lifting through neural rendering. We demonstrate the effectiveness of our LabelMaker pipeline by generating significantly better labels for the ScanNet datasets and automatically labelling the previously unlabeled ARKitScenes dataset. Code and models are available at https://labelmaker.org

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 26 of its 146 references that are in the map. First posted on arXiv 20 Nov 2023.

Builds on

26 of 146 references.

References · 26

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023Segment Anythingcited by 8,234
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  4. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  5. 2017Matterport3D: Learning from RGB-D Data in Indoor Environmentscited by 1,376
  6. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,288
  7. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 904
  8. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 864
  9. 2022Open-Vocabulary Semantic Segmentation with Mask-adapted CLIPcited by 565
  10. 2022OpenScene: 3D Scene Understanding with Open Vocabulariescited by 559
  11. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 482
  12. 2021In-Place Scene Labelling and Understanding with Implicit Scene Representationcited by 415
14 more
  1. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  2. 2023OpenMask3D: Open-Vocabulary 3D Instance Segmentationcited by 289
  3. 2022Language-Grounded Indoor 3D Semantic Segmentation in the Wildcited by 246
  4. 2022CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformerscited by 231
  5. 2023CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIPcited by 181
  6. 2022Panoptic Lifting for 3D Scene Understanding with Neural Fieldscited by 174
  7. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  8. 2022Connecting the Dots: Floorplan Reconstruction Using Two-Level Queriescited by 49
  9. 20224D-StOP: Panoptic Segmentation of 4D LiDAR using Spatio-temporal Object Proposal Generation and Aggregationcited by 35
  10. 2023AGILE3D: Attention Guided Interactive Multi-object 3D Segmentationcited by 33
  11. 2021ILabel: Interactive Neural Scene Labellingcited by 28
  12. 20223D Segmentation of Humans in Point Clouds with Synthetic Datacited by 24
  13. 2022Interactive Object Segmentation in 3D Point Cloudscited by 23
  14. 2022Unsupervised Continual Semantic Adaptation through Neural Renderingcited by 22

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 7; 2026: 2.

14 papers.

Sort:

By area:

  1. 2024Improving 2D Feature Representations by 3D-Aware Fine-Tuningcited by 71
  2. 2023Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labelscited by 64
  3. 2025Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spacescited by 54
  4. 2025Feed-Forward SceneDINO for Unsupervised Semantic Scene Completioncited by 13
  5. 2024The Bare Necessities: Designing Simple, Effective Open-Vocabulary Scene Graphscited by 11
  6. 2024ARKit LabelMaker: A New Scale for Indoor 3D Scene Understandingcited by 7
  7. 2024OpenDAS: Open-Vocabulary Domain Adaptation for 2D and 3D Segmentationcited by 6
  8. 2025Affogato: Open-Vocabulary Affordance Grounding with Automated Data Generation at Scalecited by 6
  9. 2025SLAG: Scalable Language-Augmented Gaussian Splattingcited by 4
  10. 2026OVI-MAP:Open-Vocabulary Instance-Semantic Mappingcited by 4
  11. 2025OpenCity3D: What do Vision-Language Models know about Urban Environments?cited by 3
  12. 2025Leveraging Automatic CAD Annotations for Supervised Learning in 3D Scene Understandingcited by 2
2 more
  1. 2025HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wildcited by 1
  2. 2026Hierarchical and Holistic Open-Vocabulary Functional 3D Scene Graphs for Indoor Spacescited by 1