mlsanityData to 7 Oct 2026

DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation

arXiv 2204.01599 ↗First posted 4 Apr 2022cs.CV cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Deep learning approaches achieve prominent success in 3D semantic segmentation. However, collecting densely annotated real-world 3D datasets is extremely time-consuming and expensive. Training models on synthetic data and generalizing on real-world scenarios becomes an appealing alternative, but unfortunately suffers from notorious domain shifts. In this work, we propose a Data-Oriented Domain Adaptation (DODA) framework to mitigate pattern and context gaps caused by different sensing mechanisms and layout placements across domains. Our DODA encompasses virtual scan simulation to imitate real-world point cloud patterns and tail-aware cuboid mixing to alleviate the interior context gap with a cuboid-based intermediate domain. The first unsupervised sim-to-real adaptation benchmark on 3D indoor semantic segmentation is also built on 3D-FRONT, ScanNet and S3DIS along with 7 popular Unsupervised Domain Adaptation (UDA) methods. Our DODA surpasses existing UDA approaches by over 13% on both 3D-FRONT -> ScanNet and 3D-FRONT -> S3DIS. Code is available at https://github.com/CVMI-Lab/DODA.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 59 of its 75 references that are in the map. First posted on arXiv 4 Apr 2022.

Builds on

59 of 75 references.

References · 59

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  5. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  7. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  8. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  9. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,304
  10. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  11. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  12. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
38 more
  1. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  2. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  3. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  4. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  5. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  6. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  7. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  8. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  9. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  10. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
  11. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  12. 20203D-FRONT: 3D Furnished Rooms with layOuts and semaNTicscited by 375
  13. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  14. 20203D-FUTURE: 3D Furniture shape with TextUREcited by 306
  15. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 305
  16. 2019Structured3D: A Large Photo-realistic Dataset for Structured 3D Modelingcited by 285
  17. 2018Strong-Weak Distribution Alignment for Adaptive Object Detectioncited by 269
  18. 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
  19. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  20. 2017Submanifold Sparse Convolutional Networkscited by 223
  21. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  22. 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 176
  23. 2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 158
  24. 2017Asymmetric Tri-training for Unsupervised Domain Adaptationcited by 152
  25. 2020Train in Germany, Test in The USA: Making 3D Object Detectors Generalizecited by 150
  26. 2021Self-supervised Augmentation Consistency for Adapting Semantic Segmentationcited by 149
  27. 2019xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 129
  28. 2019Meta-Sim: Learning to Generate Synthetic Datasetscited by 128
  29. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  30. 2020Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Cloudscited by 116
  31. 2019PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representationcited by 114
  32. 2019A Robust Learning Approach to Domain Adaptive Object Detectioncited by 109
  33. 2020Self-Supervised Learning for Domain Adaptation on Point-Cloudscited by 99
  34. 2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
  35. 2021Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentationcited by 87
  36. 20193D Instance Segmentation via Multi-Task Metric Learningcited by 79
  37. 2021Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigationcited by 78
  38. 2020OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasetscited by 73

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 5; 2024: 3; 2025: 3; 2026: 1.

13 papers.

Sort:

By area:

  1. 20243D Vision and Language Pretraining with Large-Scale Synthetic Datacited by 21
  2. 2024DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understandingcited by 13
  3. 2023Recent Advances in Multi-modal 3D Intelligence: A Comprehensive Survey and Evaluationcited by 12
  4. 2024Can 3D Vision-Language Models Truly Understand Natural Language?cited by 12
  5. 2023Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentationcited by 11
  6. 2025AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referringcited by 10
  7. 2022Synthetic-to-Real Domain Generalized Semantic Segmentation for 3D Indoor Point Cloudscited by 8
  8. 2023GeoAdapt: Self-Supervised Test-Time Adaptation in LiDAR Place Recognition Using Geometric Priorscited by 8
  9. 2023Cross-modal & Cross-domain Learning for Unsupervised LiDAR Semantic Segmentationcited by 4
  10. 2025Investigating Domain Gaps for Indoor 3D Object Detectioncited by 2
  11. 2023Generalized Robot 3D Vision-Language Model with Fast Rendering and Pre-Training Vision-Language Alignmentcited by 1
  12. 2025Deep Polycuboid Fitting for Compact 3D Representation of Indoor Scenescited by 0
1 more
  1. 2026CVKD-UDA: Cross-View Knowledge Distillation for 3D Unsupervised Domain Adaptive Segmentationcited by 0