SARFusion: Scene-Aware Routing Fusion for Robust Camera-LiDAR 3D Object Detection
Authors: Yuting Zhao, Ziyi Zheng, Shuxiao Li
Organizations: Institute of Automation, Chinese Academy of Sciences, Beijing, China · School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China · Wuhan College, Wuhan, China
Camera-LiDAR fusion has become a prevailing paradigm for 3D object detection in autonomous driving. However, existing fusion detectors often establish strong inter-modality dependencies by decoding object queries from tightly coupled multimodal representations. Under corrupted driving conditions, such dependencies make the detector vulnerable to unreliable modalities, where degraded observations may interfere with reliable modality-specific evidence and lead to suboptimal predictions. Moreover, modality reliability can vary across both global driving scenes and individual object queries, requiring adaptive fusion decisions at a finer granularity. To bridge this gap, we reformulate robust camera-LiDAR fusion as a scene-aware branch routing problem and propose SARFusion, a robust 3D object detector. Instead of producing detections from a single fused representation, SARFusion decouples object-query decoding into three parallel reasoning branches: a camera branch, a LiDAR branch, and a camera-LiDAR fusion branch. Guided by a Scene Reliability Prior estimated from the global driving context, SARFusion further incorporates object-level evidence to route each query to the most suitable branch. This query-wise routing strategy alleviates harmful cross-modal interference while preserving the benefits of multimodal fusion when complementary cues are trustworthy. On the nuScenes test set, SARFusion achieves strong performance with 72.5 mAP and 74.4 NDS. Extensive analyses demonstrate its robustness under challenging conditions, including sensor corruptions and environmental changes.
Figures & tables
Figure 1 : Overall architecture of the proposed SARFusion.
Figure 2 : The illustration of SRP module
Figure 3 : The illustration of SABR module.
Figure 4 : Comparison of camera-LiDAR observations under degraded sensing conditions.
Modality
Method
Validation
Test
mAP
NDS
mAP
NDS
Camera
FCOS3D [ 43 ]
34.3
41.5
35.8
42.8
PETR [ 27 ]
37.0
44.2
39.1
45.5
BEVDet [ 15 ]
–
–
42.2
48.2
LiDAR
SECOND [ 49 ]
52.6
63.0
52.8
63.3
CenterPoint [ 51 ]
59.6
66.8
60.3
67.3
Table 1 : Comparison with representative 3D object detection methods on the nuScenes validation and test sets. All results are reported in percentage.
Figure 5 : Qualitative detection results under representative adverse weather conditions, including fog, snow, and rain.
Method
Clean
Snow
Rain
Fog
Strong Sunlight
FCOS3D [ 43 ]
23.9
2.0
13.0
13.5
17.2
DETR3D [ 45 ]
34.7
5.1
20.4
27.9
34.7
PointPillars [ 23 ]
27.7
27.6
27.7
24.5
23.7
CenterPoint [ 51 ]
59.3
55.9
56.1
43.8
54.2
BEVFusion [ 30 ]
68.5
62.8
66.1
54.1
64.4
TransFusion [ 2 ]
66.4
63.3
65.4
53.7
55.1
Table 2 : Robustness comparison on the nuScenes validation set under representative weather and lighting conditions.
Setting
mAP
NDS
Single fusion branch
70.7
73.1
Multi-branch w/o routing
52.4
62.8
+ Scene-Aware Branch Routing
70.8
73.1
+ Scene Reliability Prior
71.1
73.7
Table 3 : Component ablation of SARFusion on the nuScenes validation set.
Setting
mAP
NDS
w/o scene prior supervision
69.6
72.1
w/ scene prior supervision
71.1
73.7
Table 4 : Effect of scene prior supervision on the nuScenes validation set.
Routing Evidence
mAP
NDS
Local evidence only
70.8
73.1
Scene prior + local evidence
71.1
73.7
Table 5 : Ablation of routing evidence on the nuScenes validation set.
Training Strategy
mAP
NDS
Direct training
65.7
69.6
Staged training
71.1
73.7
Table 6 : Effect of training strategy on the nuScenes validation set.