Organizations: the Shenzhen Campus of Sun Yat-sen University, Shenzhen, China · The State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China · the Beijing Academy of Artificial Intelligence, Beijing, China · the National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China · the Xi’an Research Institute of High-tech, Xi’an, China
Camera-only 3D object detection is critical for autonomous driving, offering a cost-effective alternative to LiDAR based methods. In particular, multi-view 3D object detection has emerged as a promising direction due to its balanced trade-off between performance and cost. However, existing methods often suffer significant performance degradation under complex environmental conditions such as nighttime, fog, and rain, primarily due to their reliance on training data collected mostly in ideal conditions. To address this challenge, we propose UniDA3D, a unified domain-adaptive multi-view 3D object detector designed for robust perception under diverse adverse conditions. UniDA3D formulates nighttime, rainy, and foggy scenes as a unified multi target domain adaptation problem and leverages a novel query guided domain discrepancy mitigation (QDDM) module to align object features between source and target domains at both batch and global levels via query-centric adversarial and contrastive learning. Furthermore, we introduce a domain-adaptive teacher student training pipeline with an exponential-moving-average teacher and dynamically updated high-quality pseudo labels to enhance consistency learning and suppress background noise in unlabeled target domains. In contrast to prior approaches that require separate training for each condition, UniDA3D performs a single unified training process across multiple domains, enabling robust all-weather 3D perception. On a synthesized multi-view 3D benchmark constructed by generating nighttime, rainy, and foggy counterparts from nuScenes (nuScenes-Night, nuScenes-Rain, and nuScenes-Haze), UniDA3D consistently outperforms state of-the-art camera-only multi-view 3D detectors under extreme conditions, achieving substantial gains in mAP and NDS while maintaining real-time inference efficiency.
Figures & tables
Fig. 1: Overview of the proposed UniDA3D. UniDA3D first synthesizes nighttime, rainy, and foggy multi-view images to assist training. A domain-adaptive teacher–student self-training pipeline is employed to transfer knowledge from the source domain to the target domains. UniDA3D is further equipped with a query-guided domain discrepancy mitigation (QDDM) module to align object-level features across domains at both batch and global scales.
Fig. 2: Details of the query-guided domain discrepancy mitigation (QDDM) module. QDDM leverages 3D object queries to align source and target features at the object level. It combines adversarial training and contrastive learning with dynamically updated global representation, promoting robust and consistent cross-domain 3D object detection.
Methods
Backbone
Image Size
mAP ↑
NDS ↑
mATE ↓
mASE ↓
mAOE ↓
mAVE ↓
mAAE ↓
BEVDet (CBGS) [ 40 ]
ResNet50
256 × 704
6.98
14.82
91.65
50.68
84.18
136.67
60.21
PETR [ 42 ]
ResNet50
512 × 1408
11.97
15.51
92.69
74.40
147.76
136.79
37.72
StreamPETR [ 1 ]
ResNet50
256 × 704
15.60
32.53
82.84
30.91
64.91
49.59
24.48
SOLOFusion [ 10 ]
ResNet50
256 × 704
17.84
32.91
77.64
30.78
78.28
47.02
26.41
BEVDet4D [ 9 ]
ResNet50
256 × 704
22.33
37.27
76.82
28.64
61.64
49.51
22.35
BEVFormer v2 [ 45 ]
ResNet50
640 × 1600
25.56
35.37
80.78
29.39
53.37
89.09
21.50
TABLE I: Comparison with state-of-the-art methods on the nuScenes-Night val set. Models are grouped by backbone (ResNet and V2-99) for a fair comparative analysis. Bold indicates the best result.
Table 4
Fig. 3: t-SNE visualization results (Blue point: Source Domain, Red point: Target Domain). The distribution consistency between red and blue points reflects the discrepancy in features extracted by the model. A smaller gap between the distributions indicates stronger domain adaptation capability.
EMA Ratio
mAP ↑
NDS ↑
mATE ↓
0.9
40.83
51.10
67.08
0.99
40.90
51.15
67.14
0.999
33.44
45.12
65.31
TABLE IV: Effect of EMA ratio. All experiments are conducted on nuScenes-Night val set.
Filtering threshold
mAP ↑
NDS ↑
mATE ↓
0.3
40.09
50.54
69.83
0.6
40.41
51.37
66.60
0.9
40.90
51.15
67.14
TABLE V: Effect of filtering threshold. The filtering threshold refers to the confidence threshold used to retain high-quality pseudo labels generated by the teacher model. All experiments are conducted on nuScenes-Night val set.
Self-training
QDDM
mAP ↑
NDS ↑
mATE ↓
26.78
41.58
70.93
✓
40.90
51.15
67.14
✓
41.88
51.72
65.91
✓
✓
45.04
53.76
65.87
TABLE VI: Effectiveness of Self-training and QDDM modules. All experiments are conducted on nuScenes-Night val set.
Appendix figures & tables3 assets
Supplementary material from the paper’s appendix.
Appendix
Method
Backbone
FPS
StreamPETR
ResNet-50
28.0
StreamPETR
V2-99
16.7
UniDA3D (ours)
ResNet-50
28.5
UniDA3D (ours)
V2-99
17.9
Appendix
TABLE I: Inference speed (FPS) comparison on RTX4090.
Training Method
mAP
NDS
Condition
Hybrid
45.04
53.76
Night
45.32
54.71
Rain
46.85
55.90
Haze
Night
44.93
54.44
Night
Rain
45.26
54.83
Rain
Haze
46.77
55.61
Haze
Appendix
TABLE II: Comparison of training strategies under different weather conditions.
TABLE III: Ablation on domain adversarial ( λdom ) and contrastive ( λcon ) loss weights.
Robust 3D object detection under adverse weather conditions is crucial for autonomous driving. However, most existing methods simply combine all weather samples for training while overlooking data distribution discrepancies across different weather scenarios, leading to performance conflicts. To address this issue, we introduce AW-MoE, the framework that innovatively integrates Mixture of Experts (MoE) into weather-robust multi-modal 3D object detection approaches. AW-MoE incorporates Image-guided Weather-aware Routing (IWR), which leverages the superior discriminability of image features across weather conditions and their invariance to scene variations for precise weather classification. Based on this accurate classification, IWR selects the top-K most relevant Weather-Specific Experts (WSE) that handle data discrepancies, ensuring optimal detection under all weather conditions. Additionally, we propose a Unified Dual-Modal Augmentation (UDMA) for synchronous LiDAR and 4D Radar dual-modal data augmentation while preserving the realism of scenes. Extensive experiments on the real-world dataset demonstrate that AW-MoE achieves ~ 15% improvement in adverse-weather performance over state-of-the-art methods, while incurring negligible inference overhead. Moreover, integrating AW-MoE into established baseline detectors yields performance improvements surpassing current state-of-the-art methods. These results show the effectiveness and strong scalability of our AW-MoE. We will release the code publicly at https://github.com/windlinsherlock/AW-MoE.
Hongwei Lin, Xun Huang, Chenglu Wen +1
Fujian Key Laboratory of Urban Intelligent Sensing and Computing and the School of Informatics, Xiamen University, Xiamen, FJ 361005, China · Zhongguancun Academy, Beijing, China
Robust 3D object detection under adverse weather remains a critical hurdle for autonomous driving. Despite progress with LiDAR-4D radar fusion, most methods are constrained by a closed-world assumption, implicitly requiring training and test weather to align in both type and severity. This premise fails in practice: the open-ended nature of weather, and even variations within a single type like rain, cause dramatically different LiDAR degradation patterns, leading to significant performance drops in unseen conditions. To address this, we present Dual-Critic Guided Diffusion Alignment (DCDA), a weather-agnostic framework that learns to recover degraded LiDAR features toward a clean manifold. Rather than modeling specific weather types, DCDA employs a 4D radar-conditioned diffusion process to progressively refine features, guided by two complementary critics. (i) A detection-guided critic, anchored by a pre-trained clean-weather model, ensures that the refined features retain object-level discriminability and localization accuracy. (ii) A weather adversarial critic enforces holistic distributional consistency with clean-weather representations. By aligning features through semantic and distributional constraints rather than explicit weather modeling, DCDA generalizes effectively to unseen weather types and severities without requiring paired data or weather labels. We further introduce a structured open-weather benchmark with held-out type-severity combinations and extensive experiments verify DCDA's advantages.
Shuyao Li, Chuanxing Geng, Heyang Sun +2
Nanjing University of Aeronautics and Astronautics, Nanjing, China · MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, Nanjing, China
With the advancement of autonomous driving, numerous annotated multi-modality datasets have become available. This presents an opportunity to develop domain-adaptive 3D object detectors for new environments without relying on labor-intensive manual annotations. However, traditional domain adaptation methods typically focus on a single source domain or a single modality, limiting their effectiveness in multi-source, multi-modality scenarios. In this paper, we propose a novel framework for multi-source, multi-modality unsupervised domain adaptation in 3D object detection for autonomous driving. Given multiple labeled source domains and one unlabeled target domain, our framework first introduces hierarchical spatially-conditioned (HSC) domain classifiers, which jointly align features from both camera and LiDAR modalities at two distinct levels for each source-target domain pair. To effectively leverage information from multiple source domains, we construct a prototype graph between each pair of domains. Based on this, we develop a prototype graph weighted (PGW) multi-source fusion strategy to aggregate predictions from multiple source detection heads. Experimental results on three widely used 3D object detection datasets - Waymo, nuScenes, and Lyft - demonstrate that our proposed framework effectively integrates information across both modalities and source domains, consistently outperforming state-of-the-art methods.
Xiaohu Lu, Hamed Khatounabadi, Hayder Radha
Electrical and Computer Engineering Michigan State University East Lansing, USA