mlsanityData to 7 Oct 2026

Syn-to-Real Unsupervised Domain Adaptation for Indoor 3D Object Detection

arXiv 2406.11311 ↗First posted 17 Jun 2024cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

The use of synthetic data in indoor 3D object detection offers the potential of greatly reducing the manual labor involved in 3D annotations and training effective zero-shot detectors. However, the complicated domain shifts across syn-to-real indoor datasets remains underexplored. In this paper, we propose a novel Object-wise Hierarchical Domain Alignment (OHDA) framework for syn-to-real unsupervised domain adaptation in indoor 3D object detection. Our approach includes an object-aware augmentation strategy to effectively diversify the source domain data, and we introduce a two-branch adaptation framework consisting of an adversarial training branch and a pseudo labeling branch, in order to simultaneously reach holistic-level and class-level domain alignment. The pseudo labeling is further refined through two proposed schemes specifically designed for indoor UDA. Our adaptation results from synthetic dataset 3D-FRONT to real-world datasets ScanNetV2 and SUN RGB-D demonstrate remarkable mAP25 improvements of 9.7% and 9.1% over Source-Only baselines, respectively, and consistently outperform the methods adapted from 2D and 3D outdoor scenarios. The code will be publicly available upon paper acceptance.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 33 of its 43 references that are in the map. First posted on arXiv 17 Jun 2024.

Builds on

33 of 43 references.

References · 33

  1. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  4. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  5. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  6. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  7. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
  8. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
  9. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  10. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  11. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 609
  12. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 442
21 more
  1. 2019Confidence Regularized Self-Trainingcited by 418
  2. 20203D-FRONT: 3D Furnished Rooms with layOuts and semaNTicscited by 375
  3. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 340
  4. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  5. 20183D-SIS: 3D Semantic Instance Segmentation of RGB-D Scanscited by 216
  6. 2021Group-Free 3D Object Detection via Transformerscited by 215
  7. 2020Unbiased Mean Teacher for Cross-domain Object Detectioncited by 158
  8. 2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 158
  9. 2020Train in Germany, Test in The USA: Making 3D Object Detectors Generalizecited by 150
  10. 2019Exploring Object Relation in Mean Teacher for Cross-Domain Detectioncited by 136
  11. 2020Exploring Categorical Regularization for Domain Adaptive Object Detectioncited by 130
  12. 2020Harmonizing Transferability and Discriminability for Adapting Object Detectorscited by 125
  13. 2020H3DNet: 3D Object Detection Using Hybrid Geometric Primitivescited by 123
  14. 20203DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detectioncited by 89
  15. 2021Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimationcited by 80
  16. 2021Back-tracing Representative Points for Voting-based 3D Object Detection in Point Cloudscited by 67
  17. 2020Adapting Object Detectors with Conditional Domain Normalizationcited by 55
  18. 2021Cross-View Regularization for Domain Adaptive Panoptic Segmentationcited by 41
  19. 2021MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentationcited by 16
  20. 2021See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptationcited by 15
  21. 2022HyperDet3D: Learning a Scene-conditioned 3D Object Detectorcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectivescited by 4
  2. 2026Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environmentscited by 2