This is a collection of awesome works targeting domain adaptation and generalization for 3D data. The works are roughly categorized into Uni-Modal and Multi-Modal data. Feel free to participate and add your latest work (by creating a pull-request or opening an issue), or to adapt the publication venue if it gets accepted. Inspired by awesome-domain-adaptation
Unimodal data (only 3D):
Source-Free Domain Adaptation and Test-time Adaptation
Multi-Modal data (3D (LiDAR) and image):
Others:
- A Survey on Deep Domain Adaptation for LiDAR Perception [Arxiv]
- Awesome Domain Adaptation in 3D [GitHub]
- Understanding the Domain Gap in LiDAR Object Detection Networks [Arxiv]
- Quantifying the LiDAR Sim-to-Real Domain Shift: A Detailed Investigation Using Object Detectors and Analyzing Point Clouds at Target-Level [Arxiv]
- PointDAN: A multi scale 3D Domain adaption for PointCloud Representation Network for Point Cloud Representation [NeurIPS 2019]
- A Multiclass TrAdaBoost Transfer Learning Algorithm for the Classification of Mobile LiDAR Data [ISPRS Photo and remote sensing, 2020]
- Joint Supervised and Self-Supervised Learning for 3D Real-World Challenges [ICPR 2020]
- Self-supervised Learning for Domain Adaptation on Point Clouds [WACV 2021]
- Geometry-Aware Self-Training for Unsupervised Domain Adaptation on Object Point Clouds [ICCV 2021]
- RefRec: Pseudo-labels Refinement via Shape Reconstruction for Unsupervised 3D Domain Adaptation [3DV 2021]
- A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds [Arxiv]
- Generation For Adaption: A GAN-Based Approach for Unsupervised Domain Adaption with 3D Point Cloud Data [Arxiv]
- Self-Distillation for Unsupervised 3D Domain Adaptation [WACV 2022]
- Domain Adaptation on Point Clouds via Geometry-Aware Implicits [CVPR 2022]
- Self-Supervised Global-Local Structure Modeling for Point Cloud Domain Adaptation with Reliable Voted Pseudo Labels [CVPR 2022]
- MEnsA: Mix-up Ensemble Average for Unsupervised Multi Target Domain Adaptation on 3D Point Clouds [CVPRw 2023]
- Progressive Target-Styled Feature Augmentation for Unsupervised Domain Adaptation on Point Clouds [Arxiv]
- Progressive Classifier and Feature Extractor Adaptation for Unsupervised Domain Adaptation on Point Clouds [ECCV 2024]
- Finetuning Pre-trained Model with Limited Data for LiDAR-based 3D Object Detection by Bridging Domain Gaps [Arxiv]
- LiDAR Sensor modeling and Data augmentation with GANs for Autonomous driving [Arxiv]
- Domain adaptation for vehicle detection from bird’s eye view LiDar Point cloud data [Arxiv]
- Unsupervised Neural Sensor Models for Synthetic LiDAR Data Augmentation [Arxiv]
- Range Adaptation for 3D Object Detection in LiDAR [Arxiv]
- Cross-Sensor deep domain adaptation through self supervision [Paper]
- Train in Germany, Test in The USA: Making 3D Object Detectors Generalize [CVPR 2020]
- SRDAN: Scale-aware and Range-aware Domain Adaptation Network for Cross-dataset 3D Object Detection [CVPR 2021]
- ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection [CVPR 2021]
- SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation [ICCV 2021]
- Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency [ICCV 2021]
- Learning Transferable Features for Point Cloud Detection via 3D Contrastive Co-training [NeurIPS 2021]
- Unsupervised Subcategory Domain Adaptive Network for 3D Object Detection in LiDAR [Electronics 2021]
- Pseudo-labeling for Scalable 3D Object Detection [Arxiv]
- Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detection [Arxiv]
- ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection [Arxiv]
- Uncertainty-aware Mean Teacher for Source-free Unsupervised Domain Adaptive 3D Object Detection [Arxiv]
- Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection [Arxiv]
- Adversarial Training on Point Clouds for Sim-to-Real 3D Object Detection [Paper]
- Investigating the Impact of Multi-LiDAR Placement on Object Detection for Autonomous Driving [CVPR 2022]
- LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection [ECCV 2022]
- Real-Time and Robust 3D Object Detection Within Road-Side LiDARs Using Domain Adaptation [Arxiv]
- Towards Robust 3D Object Recognition with Dense-to-Sparse Deep Domain Adaptation [Arxiv]
- Robust 3D Object Detection in Cold Weather Conditions [Arxiv]
- CONTEXT-AWARE DATA AUGMENTATION FOR LIDAR 3D OBJECT DETECTION [Arxiv]
- CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detection [Arxiv]
- SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud [Arxiv]
- Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection [CVPR 2023]
- Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection [CVPR 2023]
- Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling [ICCV 2023]
- GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Clouds [ICCV 2023]
- SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud [AAAI 2023]
- WLST: Weak Labels Guided Self-training for Weakly-supervised Domain Adaptation on 3D Object Detection [Arxiv]
- Gradient-based Maximally Interfered Retrieval for Domain Incremental 3D Object Detection [Arxiv]
- MS3D: Leveraging Multiple Detectors for Unsupervised Domain Adaptation in 3D Object Detection [Arxiv]
-
SOAP: Cross-sensor Domain Adaptation for 3D Object Detection Using Stationary Object Aggregation Pseudo-labelling [WACV 2024]
-
Pseudo Label Refinery for Unsupervised Domain Adaptation on Cross-dataset 3D Object Detection [CVPR 2024]
-
CMD: A Cross Mechanism Domain Adaptation Dataset for 3D Object Detection [ECCV 2024]
-
UADA3D: Unsupervised Adversarial Domain Adaptation for 3D Object Detection with Sparse LiDAR and Large Domain Gaps [IEEE RA-L]
-
LiT: Unifying LiDAR “Languages” with LiDAR Translator [NeurIPS 2024]
-
Syn-to-Real Unsupervised Domain Adaptation for Indoor 3D Object Detection [Arxiv]
-
Semi-Supervised Domain Adaptation Using Target-Oriented Domain Augmentation for 3D Object Detection [Arxiv]
-
CTS: Sim-to-Real Unsupervised Domain Adaptation on 3D Detection [Arxiv]
-
STAL3D: Unsupervised Domain Adaptation for 3D Object Detection via Collaborating Self-Training and Adversarial Learning [Arxiv]
-
DALI: Domain Adaptive LiDAR Object Detection via Distribution-level and Instance-level Pseudo Label Denoising [Arxiv]
- SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud [ICRA 2019]
- ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation [AAAI 2021]
- Analyzing the Cross-Sensor Portability of Neural Network Architectures for LiDAR-based Semantic Labeling [Arxiv]
- Domain Transfer for Semantic Segmentation of LiDAR Data using Deep Neural Networks [IROS 2020]
- Unsupervised scene adaptation for semantic segmentation of urban mobile laser scanning point clouds [ISPRS Photo and remote sensing 2020]
- Improved Semantic Segmentation of Low-Resolution 3D Point Clouds Using Supervised Domain Adaptation [NILES 2020]
- Domain Adaptation in LiDAR Semantic Segmentation by Aligning Class Distributions [Arxiv]
- Point-Based Multilevel Domain Adaptation for Point Cloud Segmentation [Paper]
- Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds [CVPR 2021]
- Unsupervised Domain Adaptive Point Cloud Semantic Segmentation [ACPR 2021]
- Cycle and Semantic Consistent Adversarial Domain Adaptation for Reducing Simulation-to-Real Domain Shift in LiDAR Bird’s Eye View [ITSC 2021]
- HYLDA: End-to-end Hybrid Learning Domain Adaptation for LiDAR Semantic Segmentation [Arxiv]
- Unsupervised Domain Adaptation in LiDAR Semantic Segmentation with Self-Supervision and Gated Adapters [Arxiv]
- LiDARNet: A Boundary-Aware Domain Adaptation Model for Point Cloud Semantic Segmentation [Arxiv]
- Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation [AAAI 2022]
- Unsupervised Domain Adaptation for Point Cloud Semantic Segmentation via Graph Matching [IROS 2022]
- DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Indoor Semantic Segmentation [ECCV 2022]
- CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation [ECCV 2022]
- Enhanced Prototypical Learning for Unsupervised Domain Adaptation in LiDAR Semantic Segmentation [Arxiv]
- Fake it, Mix it, Segment it: Bridging the Domain Gap Between Lidar Sensors [Arxiv]
- ADAS: A Simple Active-and-Adaptive Baseline for Cross-Domain 3D Semantic Segmentation [Arxiv]
- Domain Adaptation in LiDAR Semantic Segmentation via Alternating Skip Connections and Hybrid Learning [Arxiv]
- T–UDA: Temporal Unsupervised Domain Adaptation in Sequential Point Clouds [IROS 2023]
- Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation [TPAMI 2023]
- Adversarially Masking Synthetic to Mimic Real: Adaptive Noise Injection for Point Cloud Segmentation Adaptation [CVPR 2023]
- Adversarially Masking Synthetic to Mimic Real:Adaptive Noise Injection for Point Cloud Segmentation Adaptation [CVPR 2023]
- LiDAR-UDA: Self-ensembling Through Time for Unsupervised LiDAR Domain Adaptation [ICCV 2023]
- ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenation [ICRA 2023]
- Prototype-Guided Multitask Adversarial Network for Cross-Domain LiDAR Point Clouds Semantic Segmentation [IEEE Transactions on Geoscience and Remote Sensing 2023]
- SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation [3DV 2024]
- Construct to Associate: Cooperative Context Learning for Domain Adaptive Point Cloud Segmentation [CVPR 2024]
- Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Clouds [CVPR 2024]
- Contrastive Maximum Mean Discrepancy for Unsupervised Domain Adaptation Applied to Large Scale 3D LiDAR Semantic Segmentation [Paper]
- LiOn-XA: Unsupervised Domain Adaptation via LiDAR-Only Cross-Modal Adversarial Training[ArXiv]
- SF-UDA3D: Source-Free Unsupervised Domain Adaptation for LiDAR-Based 3D Object Detection [3DV 2020]
- GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation [ECCV 2022]
- Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation [ECCV 2024]
- HGL: Hierarchical Geometry Learning for Test-time Adaptation in 3D Point Cloud Segmentation [ECCV 2024]
- MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection [Arxiv]
- CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformation [Arxiv]
- Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Models [Arxiv]
- 3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection [CVPR 2022]
- Synthetic-to-Real Domain Generalized Semantic Segmentation for 3D Indoor Point Clouds [Arxiv]
- Instant Domain Augmentation for LiDAR Semantic Segmentation [CVPR 2023]
- Single Domain Generalization for LiDAR Semantic Segmentation [CVPR 2023]
- 3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds [CVPR 2023]
- Domain generalization of 3D semantic segmentation in autonomous driving [ICCV 2023]
- Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation [ICCV 2023]
- Robo3D: Towards Robust and Reliable 3D Perception against Corruptions [ICCV 2023]
- 3D Adversarial Augmentations for Robust Out-of-Domain Predictions [IJCV]
- Domain Generalization of 3D Object Detection by Density-Resampling [Arxiv]
- Domain Generalization in LiDAR Semantic Segmentation Leveraged by Density Discriminative Feature Embedding [Arxiv]
- UniMix: Towards Domain Adaptive and Generalizable LiDAR Semantic Segmentation in Adverse Weather [CVPR 2024]
- An Empirical Study of the Generalization Ability of Lidar 3D Object Detectors to Unseen Domains [CVPR 2024]
- Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weather [ECCV 2024]
- DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understanding [ECCV 2024]
- xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation [CVPR 2020]
- Adversarial unsupervised domain adaptation for 3D semantic segmentation with multi-modal learning [ISPRS 2021]
- mDALU: Multi-Source Domain Adaptation and Label Unification with Partial Datasets [ICCV 2021]
- Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation [ICCV 2021]
- See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptation [Arxiv]
- MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation [CVPR 2022]
- Self-supervised Exclusive Learning for 3D Segmentation with Cross-Modal Unsupervised Domain Adaptation [ACM 2022]
- Cross-Domain and Cross-Modal Knowledge Distillation in Domain Adaptation for 3D Semantic Segmentation [ACM 2022]
- Cross-modal & Cross-domain Learning for Unsupervised LiDAR Semantic Segmentation [ACM 2023]
- Cross-modal Unsupervised Domain Adaptation for 3D Semantic Segmentation via Bidirectional Fusion-then-Distillation [ACM 2023]
- Cross-Modal Contrastive Learning for Domain Adaptation in 3D Semantic Segmentation [AAAI 2023]
- Exploiting the Complementarity of 2D and 3D Networks to Address Domain-Shift in 3D Semantic Segmentation [CVPR 2023]
- Mx2M: Masked Cross-Modality Modeling in Domain Adaptation for 3D Semantic Segmentation [AAAI 2023]
- CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-based 3D Object Detection [AAAI 2024]
- Learning to Adapt SAM for Segmenting Cross-domain Point Clouds [ECCV 2024]
- MoPA: Multi-Modal Prior Aided Domain Adaptation for 3D Semantic Segmentation [ICRA 2024]
- UniDSeg: Unified Cross-Domain 3D Semantic Segmentation via Visual Foundation Models Prior [NeurIPS 2024]
- Multimodal 3D Object Detection on Unseen Domains [Arxiv]
- Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation [Arxiv]
- TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models [Arxiv]
- Fusion-then-Distillation: Toward Cross-modal Positive Distillation for Domain Adaptive 3D Semantic Segmentation [Arxiv]
- CNN-based synthesis of realistic high-resolution LiDAR data [IEEE Intelligent Vehicles Symposium]
- Learning to Drop Points for LiDAR Scan Synthesis [Arxiv]
- LiDAR Snowfall Simulation for Robust 3D Object Detection [CVPR 2022]
- SLiDE: Self-supervised LiDAR De-snowing through Reconstruction Difficulty [ECCV 2022]
- Learning to Simulate Realistic LiDARs [IROS 2022]
- DiffCloud: Real-to-Sim from Point Clouds with Differentiable Simulation and Rendering of Deformable Objects [Arxiv]
- Towards Zero Domain Gap: A Comprehensive Study of Realistic LiDAR Simulation for Autonomy Testing [ICCV 2023]
- Weakly-Supervised Domain Adaptation via GAN and Mesh Model for Estimating 3D Hand Poses Interacting Objects [CVPR 2020]
- Project to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor Data [ACCV 2020]
- A Registration-Aided Domain Adaptation Network for 3D Point Cloud Based Place Recognition [IROS 2021]
- Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency [Arxiv]
- Anatomy-guided domain adaptation for 3D in-bed human pose estimation [Arxiv]