# PanDA: Unsupervised Domain Adaptation for Multimodal 3D Panoptic Segmentation in Autonomous Driving

arXiv: https://arxiv.org/abs/2604.19379 · HTML: https://mlsanity.com/paper/2604.19379/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 49 of its 66 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Builds on (most cited first, 30 of 49)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Panoptic Segmentation](https://mlsanity.com/paper/1801.00868/) (2018)
- [Segment Everything Everywhere All at Once](https://mlsanity.com/paper/2304.06718/) (2023)
- [MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation](https://mlsanity.com/paper/2212.01322/) (2022)
- [Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking](https://mlsanity.com/paper/2109.03805/) (2021)
- [xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/1911.12676/) (2019)
- [Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation](https://mlsanity.com/paper/2103.14962/) (2021)
- [SESS: Self-Ensembling Semi-Supervised 3D Object Detection](https://mlsanity.com/paper/1912.11803/) (2019)
- [LiDAR-based Panoptic Segmentation via Dynamic Shifting Network](https://mlsanity.com/paper/2011.11964/) (2020)
- [EfficientLPS: Efficient LiDAR Panoptic Segmentation](https://mlsanity.com/paper/2102.08009/) (2021)
- [MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2204.12667/) (2022)
- [LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception](https://mlsanity.com/paper/2209.09385/) (2022)
- [Panoptic-PHNet: Towards Real-Time and High-Precision LiDAR Panoptic Segmentation via Clustering Pseudo Heatmap](https://mlsanity.com/paper/2205.07002/) (2022)
- [CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation](https://mlsanity.com/paper/2207.09778/) (2022)
- [PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness](https://mlsanity.com/paper/2312.02158/) (2023)
- [Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentation](https://mlsanity.com/paper/2101.07253/) (2021)
- [GP-S3Net: Graph-based Panoptic Sparse Semantic Segmentation Network](https://mlsanity.com/paper/2108.08401/) (2021)
- [Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection](https://mlsanity.com/paper/2304.09446/) (2023)
- [Sparse Cross-scale Attention Network for Efficient LiDAR Panoptic Segmentation](https://mlsanity.com/paper/2201.05972/) (2022)
- [Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training](https://mlsanity.com/paper/2204.11590/) (2022)
- [4D Panoptic Scene Graph Generation](https://mlsanity.com/paper/2405.10305/) (2024)
- [Learning to Adapt SAM for Segmenting Cross-domain Point Clouds](https://mlsanity.com/paper/2310.08820/) (2023)
- [Unsupervised Domain Adaptation for LiDAR Panoptic Segmentation](https://mlsanity.com/paper/2109.15286/) (2021)
- [LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment](https://mlsanity.com/paper/2308.01686/) (2023)
- [Position-Guided Point Cloud Panoptic Segmentation Transformer](https://mlsanity.com/paper/2303.13509/) (2023)
- [EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation](https://mlsanity.com/paper/2304.14291/) (2023)
- [MoPA: Multi-Modal Prior Aided Domain Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2309.11839/) (2023)

## Abstract (arXiv)

This paper presents the first study on Unsupervised Domain Adaptation (UDA) for multimodal 3D panoptic segmentation (mm-3DPS), aiming to improve generalization under domain shifts commonly encountered in real-world autonomous driving. A straightforward solution is to employ a pseudo-labeling strategy, which is widely used in UDA to generate supervision for unlabeled target data, combined with an mm-3DPS backbone. However, existing supervised mm-3DPS methods rely heavily on strong cross-modal complementarity between LiDAR and RGB inputs, making them fragile under domain shifts where one modality degrades (e.g., poor lighting or adverse weather). Moreover, conventional pseudo-labeling typically retains only high-confidence regions, leading to fragmented masks and incomplete object supervision, which are issues particularly detrimental to panoptic segmentation. To address these challenges, we propose PanDA, the first UDA framework specifically designed for multimodal 3D panoptic segmentation. To improve robustness against single-sensor degradation, we introduce an asymmetric multimodal augmentation that selectively drops regions to simulate domain shifts and improve robust representation learning. To enhance pseudo-label completeness and reliability, we further develop a dual-expert pseudo-label refinement module that extracts domain-invariant priors from both 2D and 3D modalities. Extensive experiments across diverse domain shifts, spanning time, weather, location, and sensor variations, significantly surpass state-of-the-art UDA baselines for 3D semantic segmentation.