mlsanityData to 7 Oct 2026

DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding

arXiv 2407.08801 ↗First posted 11 Jul 2024cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Recent point cloud understanding research suffers from performance drops on unseen data, due to the distribution shifts across different domains. While recent studies use Domain Generalization (DG) techniques to mitigate this by learning domain-invariant features, most are designed for a single task and neglect the potential of testing data. Despite In-Context Learning (ICL) showcasing multi-task learning capability, it usually relies on high-quality context-rich data and considers a single dataset, and has rarely been studied in point cloud understanding. In this paper, we introduce a novel, practical, multi-domain multi-task setting, handling multiple domains and multiple tasks within one unified model for domain generalized point cloud understanding. To this end, we propose Domain Generalized Point-In-Context Learning (DG-PIC) that boosts the generalizability across various tasks and domains at testing time. In particular, we develop dual-level source prototype estimation that considers both global-level shape contextual and local-level geometrical structures for representing source domains and a dual-level test-time feature shifting mechanism that leverages both macro-level domain semantic information and micro-level patch positional relationships to pull the target data closer to the source ones during the testing. Our DG-PIC does not require any model updates during the testing and can handle unseen domains and multiple tasks, textiti.e., point cloud reconstruction, denoising, and registration, within one unified model. We also introduce a benchmark for this new setting. Comprehensive experiments demonstrate that DG-PIC outperforms state-of-the-art techniques significantly.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 68 of its 78 references that are in the map. First posted on arXiv 11 Jul 2024.

Builds on

68 of 78 references.

References · 68

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
  10. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  11. 2020PCT: Point cloud transformercited by 730
  12. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
38 more
  1. 2021Learning To Retrieve Prompts for In-Context Learningcited by 641
  2. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  3. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  4. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  5. 2022Images Speak in Images: A Generalist Painter for In-Context Visual Learningcited by 317
  6. 2022Visual Prompting via Image Inpaintingcited by 248
  7. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  8. 2023What Makes Good Examples for Visual In-Context Learning?cited by 150
  9. 2020Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Cloudscited by 116
  10. 2019PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representationcited by 114
  11. 2020PointMixup: Augmentation for Point Cloudscited by 104
  12. 2020Self-Supervised Learning for Domain Adaptation on Point-Cloudscited by 99
  13. 2021SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generationcited by 93
  14. 2021Context-Aware Mixup for Domain Adaptive Semantic Segmentationcited by 79
  15. 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
  16. 2023Exploring Diverse In-Context Configurations for Image Captioningcited by 63
  17. 2020ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentationcited by 56
  18. 2024Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Modelscited by 51
  19. 20233D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Cloudscited by 46
  20. 2020Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentationcited by 45
  21. 2020Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practicecited by 43
  22. 20213D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detectioncited by 43
  23. 2023Instance-Aware Domain Generalization for Face Anti-Spoofingcited by 42
  24. 2023Explore In-Context Learning for 3D Point Cloud Understandingcited by 40
  25. 2021No-Reference Point Cloud Quality Assessment via Domain Adaptationcited by 37
  26. 2022SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloudcited by 37
  27. 2019Domain Adaptation for Vehicle Detection from Bird's Eye View LiDAR Point Cloud Datacited by 35
  28. 2022Generative Domain Adaptation for Face Anti-Spoofingcited by 33
  29. 2021Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Cloudscited by 31
  30. 2023How to Configure Good In-Context Sequence for Visual Question Answeringcited by 31
  31. 2021PIT: Position-Invariant Transform for Cross-FoV Domain Adaptationcited by 30
  32. 2022Masked Autoencoders in 3D Point Cloud Representation Learningcited by 30
  33. 2021Self-Adversarial Disentangling for Specific Domain Adaptationcited by 29
  34. 2023Neuron Structure Modeling for Generalizable Remote Physiological Measurementcited by 29
  35. 2022Adaptive Mixture of Experts Learning for Generalizable Face Anti-Spoofingcited by 28
  36. 2023Towards Domain Generalization for Multi-view 3D Object Detection in Bird-Eye-Viewcited by 27
  37. 2024CAT-SAM: Conditional Tuning for Few-Shot Adaptation of Segment Anything Modelcited by 27
  38. 2021Domain Adaptation on Point Clouds via Geometry-Aware Implicitscited by 26

50 most cited of 68 All 68 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 4; 2026: 3.

13 papers.

Sort:

By area:

  1. 2024Number it: Temporal Grounding Videos like Flipping Mangacited by 65
  2. 2024Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentationcited by 20
  3. 2025Mimic In-Context Learning for Multimodal Taskscited by 12
  4. 2024PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understandingcited by 11
  5. 2024MICAS: Multi-grained In-Context Adaptive Sampling for 3D Point Cloud Processingcited by 5
  6. 2025Domain Generalization via Discrete Codebook Learningcited by 3
  7. 2024DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completioncited by 2
  8. 2025Improving Multimodal Distillation for 3D Semantic Segmentation under Domain Shiftcited by 2
  9. 2026PromptHub: Enhancing Multi-Prompt Visual In-Context Learning with Locality-Aware Fusion, Concentration and Alignmentcited by 2
  10. 2024Source-Free Test-Time Adaptation For Online Surface-Defect Detectioncited by 0
  11. 2025Generative Classifier for Domain Generalizationcited by 0
  12. 2026Mamba Learns in Context: Structure-Aware Domain Generalization for Multi-Task Point Cloud Understandingcited by 0
1 more
  1. 2026Deformation-based In-Context Learning for Point Cloud Understandingcited by 0