# Domain Adaptation on Point Clouds via Geometry-Aware Implicits

arXiv: https://arxiv.org/abs/2112.09343 · HTML: https://mlsanity.com/paper/2112.09343/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 42 references that are in the map.
- First posted on arXiv 17 Dec 2021.

## Builds on (most cited first, 30 of 33)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [CyCADA: Cycle-Consistent Adversarial Domain Adaptation](https://mlsanity.com/paper/1711.03213/) (2017)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1712.02560/) (2017)
- [Contrastive Adaptation Network for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1901.00976/) (2019)
- [Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks](https://mlsanity.com/paper/1612.05424/) (2016)
- [Learning from Simulated and Unsupervised Images through Adversarial Training](https://mlsanity.com/paper/1612.07828/) (2016)
- [ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection](https://mlsanity.com/paper/2103.05346/) (2021)
- [Asymmetric Tri-training for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1702.08400/) (2017)
- [Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds](https://mlsanity.com/paper/2007.08488/) (2020)
- [PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation](https://mlsanity.com/paper/1911.02744/) (2019)
- [Self-Supervised Learning for Domain Adaptation on Point-Clouds](https://mlsanity.com/paper/2003.12641/) (2020)
- [Beyond Sharing Weights for Deep Domain Adaptation](https://mlsanity.com/paper/1603.06432/) (2016)
- [AutoDIAL: Automatic DomaIn Alignment Layers](https://mlsanity.com/paper/1704.08082/) (2017)
- [Self-supervised Learning of Point Clouds via Orientation Estimation](https://mlsanity.com/paper/2008.00305/) (2020)
- [ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation](https://mlsanity.com/paper/2009.03456/) (2020)
- [Domain Adaptation for Vehicle Detection from Bird's Eye View LiDAR Point Cloud Data](https://mlsanity.com/paper/1905.08955/) (2019)
- [Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds](https://mlsanity.com/paper/2108.09169/) (2021)
- [Joint Supervised and Self-Supervised Learning for 3D Real-World Challenges](https://mlsanity.com/paper/2004.07392/) (2020)
- [RefRec: Pseudo-labels Refinement via Shape Reconstruction for Unsupervised 3D Domain Adaptation](https://mlsanity.com/paper/2110.11036/) (2021)

## Built on by (most cited first, 26 of 26)

- [MATE: Masked Autoencoders are Online 3D Test-Time Learners](https://mlsanity.com/paper/2211.11432/) (2022)
- [SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation](https://mlsanity.com/paper/2304.03251/) (2023)
- [A Survey of Label-Efficient Deep Learning for 3D Point Clouds](https://mlsanity.com/paper/2305.19812/) (2023)
- [Backpropagation-free Network for 3D Test-time Adaptation](https://mlsanity.com/paper/2403.18442/) (2024)
- [DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding](https://mlsanity.com/paper/2407.08801/) (2024)
- [Self-Distillation for Unsupervised 3D Domain Adaptation](https://mlsanity.com/paper/2210.08226/) (2022)
- [Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2310.20293/) (2023)
- [CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformation](https://mlsanity.com/paper/2407.16193/) (2024)
- [PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding](https://mlsanity.com/paper/2411.00632/) (2024)
- [Anatomy-guided domain adaptation for 3D in-bed human pose estimation](https://mlsanity.com/paper/2211.12193/) (2022)
- [SCoDA: Domain Adaptive Shape Completion for Real Scans](https://mlsanity.com/paper/2304.10179/) (2023)
- [SUG: Single-dataset Unified Generalization for 3D Point Cloud Classification](https://mlsanity.com/paper/2305.09160/) (2023)
- [Synergizing Contrastive Learning and Optimal Transport for 3D Point Cloud Domain Adaptation](https://mlsanity.com/paper/2308.14126/) (2023)
- [PC-Adapter: Topology-Aware Adapter for Efficient Domain Adaption on Point Clouds with Rectified Pseudo-label](https://mlsanity.com/paper/2309.16936/) (2023)
- [TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models](https://mlsanity.com/paper/2403.11691/) (2024)
- [MaskLRF: Self-supervised Pretraining via Masked Autoencoding of Local Reference Frames for Rotation-invariant 3D Point Set Analysis](https://mlsanity.com/paper/2403.00206/) (2024)
- [Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis](https://mlsanity.com/paper/2503.12150/) (2025)
- [PatchMixer: Rethinking network design to boost generalization for 3D point cloud understanding](https://mlsanity.com/paper/2307.15692/) (2023)
- [Progressive Classifier and Feature Extractor Adaptation for Unsupervised Domain Adaptation on Point Clouds](https://mlsanity.com/paper/2311.16474/) (2023)
- [Spatially-Delineated Domain-Adapted AI Classification: An Application for Oncology Data](https://mlsanity.com/paper/2501.11695/) (2025)
- [CLIPoint3D: Language-Grounded Few-Shot Unsupervised 3D Point Cloud Domain Adaptation](https://mlsanity.com/paper/2602.20409/) (2026)
- [Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers](https://mlsanity.com/paper/2407.18534/) (2024)
- [Bridging Domain Gap of Point Cloud Representations via Self-Supervised Geometric Augmentation](https://mlsanity.com/paper/2409.06956/) (2024)
- [Curvature Diversity-Driven Deformation and Domain Alignment for Point Cloud](https://mlsanity.com/paper/2410.02720/) (2024)
- [Locating and Mitigating Gradient Conflicts in Point Cloud Domain Adaptation via Saliency Map Skewness](https://mlsanity.com/paper/2504.15796/) (2025)
- [Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition](https://mlsanity.com/paper/2506.21165/) (2025)

## Abstract (arXiv)

As a popular geometric representation, point clouds have attracted much attention in 3D vision, leading to many applications in autonomous driving and robotics. One important yet unsolved issue for learning on point cloud is that point clouds of the same object can have significant geometric variations if generated using different procedures or captured using different sensors. These inconsistencies induce domain gaps such that neural networks trained on one domain may fail to generalize on others. A typical technique to reduce the domain gap is to perform adversarial training so that point clouds in the feature space can align. However, adversarial training is easy to fall into degenerated local minima, resulting in negative adaptation gains. Here we propose a simple yet effective method for unsupervised domain adaptation on point clouds by employing a self-supervised task of learning geometry-aware implicits, which plays two critical roles in one shot. First, the geometric information in the point clouds is preserved through the implicit representations for downstream tasks. More importantly, the domain-specific variations can be effectively learned away in the implicit space. We also propose an adaptive strategy to compute unsigned distance fields for arbitrary point clouds due to the lack of shape models in practice. When combined with a task loss, the proposed outperforms state-of-the-art unsupervised domain adaptation methods that rely on adversarial domain alignment and more complicated self-supervised tasks. Our method is evaluated on both PointDA-10 and GraspNet datasets. The code and trained models will be publicly available.