RLPR: Radar-to-LiDAR Place Recognition via Two-Stage Asymmetric Cross-Modal Alignment for Autonomous Driving

Zhangshuo Qi; Jingyi Xu; Luqi Cheng; Shichen Wen; Guangming Xiong

cs.CVMar 9, 2026

RLPR: Radar-to-LiDAR Place Recognition via Two-Stage Asymmetric Cross-Modal Alignment for Autonomous Driving

Authors: Zhangshuo Qi, Jingyi Xu, Luqi Cheng, Shichen Wen, Guangming Xiong

Organizations: Beijing Institute of Technology, Beijing, 100081, China. · Shanghai Jiaotong University, Shanghai, 200240, China.

Abstract

All-weather autonomy is critical for autonomous driving, which necessitates reliable localization across diverse scenarios. While LiDAR place recognition is widely deployed for this task, its performance degrades in adverse weather. Conversely, radar-based methods, though weather-resilient, are hindered by the general unavailability of radar maps. To bridge this gap, radar-to-LiDAR place recognition, which localizes radar scans within existing LiDAR maps, has garnered increasing interest. However, extracting discriminative and generalizable features shared between modalities remains challenging, compounded by the scarcity of large-scale paired training data and the signal heterogeneity across radar types. In this work, we propose RLPR, a robust radar-to-LiDAR place recognition framework compatible with single-chip, scanning, and 4D radars. We first design a dual-stream network to extract structural features that abstract away from sensor-specific signal properties (e.g., Doppler or RCS). Subsequently, motivated by our task-specific asymmetry observation between radar and LiDAR, we introduce a two-stage asymmetric cross-modal alignment (TACMA) strategy, which leverages the pre-trained radar branch as a discriminative anchor to guide the alignment process. Experiments on four datasets demonstrate that RLPR achieves state-of-the-art recognition accuracy with strong zero-shot generalization capabilities.

Figures & tables

Fig. 1: Conceptual overview of the proposed RLPR framework. (a) RLPR facilitates robust place recognition across radar types. (b) Existing methods perform symmetric feature alignment. (c) Motivated by the task‑specific asymmetry between radar and LiDAR, we design a two-stage asymmetric cross-modal alignment (TACMA) strategy that enables effective feature alignment.

Fig. 2: The system overview of RLPR. The proposed radar-to-LiDAR place recognition framework consists of a dual-stream network and the two-stage asymmetric cross-modal alignment (TACMA) strategy. The dual-stream network is designed to extract global and local geometric features, while the TACMA strategy exploits cross-modal commonalities for accurate and generalizable retrieval.

Fig. 3: Architecture of the proposed Polar Context Enhancer. It captures global dependencies through two-way scanning along range and azimuth axes, generating an importance map to gate the polar BEV. The corresponding images share the same color scale.

Fig. 4: Representational evolution under pre-training. Modality-specific place recognition pre-training induces relatively larger radar entropy gain with concurrent gains in separability. The polar BEV feature visualizations are also provided.

Methods	MulRan-Riverside				MulRan-DCC				Bor-Clear
	AR@1	AR@5	AR@10	max $F_{1}$	AR@1	AR@5	AR@10	max $F_{1}$	AR@1	AR@5	AR@10	max $F_{1}$
KidnappedRadar-CM [ 26 ]	5.452	12.94	20.30	0.1286	9.575	23.94	42.02	0.2222	0.6890	2.493	4.133	0.02755
BEVPlace++-CM [ 18 ]	2.668	10.21	16.94	0.05198	2.660	10.64	21.81	0.07207	0.6562	2.067	3.642	0.01377
LIP-Loc [ 23 ]	7.135	17.40	23.43	0.1024	9.574	26.06	39.36	0.4000	0.7532	2.636	4.759	0.005448
I2P-CMPR [ 30 ]	4.292	19.84	31.73	0.01497	5.851	21.81	31.38	0.08163	3.771	12.12	19.58	0.01304
Radar-to-LiDAR [ 31 ]	31.13	44.54	50.96	0.4748	12.77	24.47	32.98	0.2264	24.51	49.61	61.25	0.3938

TABLE I: Scanning radar-to-LiDAR performance on MulRan & Boreas

Methods	BS				SON				SQ
	AR@1	AR@5	AR@10	max $F_{1}$	AR@1	AR@5	AR@10	max $F_{1}$	AR@1	AR@5	AR@10	max $F_{1}$
AutoPlace-CM [ 4 ]	64.65	76.48	79.51	0.7890	0.9072	1.693	2.510	0.01822	0.4706	2.353	3.177	0.03540
BEVPlace++-CM [ 18 ]	1.380	5.087	8.333	0.07576	0.7557	3.023	5.441	0.04545	4.935	16.80	25.73	0.09524
LIP-Loc [ 23 ]	14.64	30.07	37.94	0.2615	2.328	8.620	14.18	0.07122	5.882	18.45	26.79	0.1681
I2P-CMPR [ 30 ]	12.31	26.17	34.45	0.2635	15.84	34.07	42.65	0.3192	18.45	38.43	48.06	0.3518
RLPR (ours)	70.85	80.30	82.79	0.8907	59.31	77.42	83.07	0.7582	47.71	60.63	66.04	0.6893

TABLE II: Phased-array 3D radar-to-LiDAR performance on nuScenes

Method	81r			SportsComplex
Method	AR@1	AR@5	max $F_{1}$	AR@1	AR@5	max $F_{1}$
TransLoc4D-CM [ 22 ]	13.73	19.82	0.4015	21.35	33.43	0.5437
BEVPlace++-CM [ 18 ]	0.4884	0.5215	0.04369	2.879	6.930	0.09195
LIP-Loc [ 23 ]	7.427	18.00	0.1319	10.38	26.07	0.1796
I2P-CMPR [ 30 ]	16.26	17.51	0.4118	32.40	39.88	0.6049
RLPR (ours)	44.71	47.58	0.6304	72.16	82.62	0.8418

TABLE III: Phased-array 4D radar-to-LiDAR performance

Strategy	BS		SON		SQ		Riverside		DCC		Bor-Clear		81r
	AR@1	AR@5	AR@1	AR@5	AR@1	AR@5	AR@1	AR@5	AR@1	AR@5	AR@1	AR@5	AR@1	AR@5
No Pre-training	20.35	39.69	5.804	15.39	3.760	12.34	8.469	19.55	10.64	35.11	3.018	5.053	29.85	32.21
Joint Optimization	44.18	60.90	24.88	38.15	20.21	33.37	21.64	39.56	22.87	48.40	17.03	21.95	32.83	34.29
Anchor-Only Pre-Training	60.14	75.07	22.43	42.50	23.74	42.19	34.17	55.51	32.98	60.64	30.87	39.07	28.04	30.60
Modality-Specific Pre-Training	70.85	80.30	59.31	77.42	47.71	60.63	64.85	78.77	55.32	73.94	87.60	94.26	44.71	47.58

TABLE IV: Ablation study on place recognition pre-training

Loss	Alignment Strategy	BS		SON		SQ		Riverside		DCC		Bor-Clear		81r
		AR@1	AR@5	AR@1	AR@5	AR@1	AR@5	AR@1	AR@5	AR@1	AR@5	AR@1	AR@5	AR@1	AR@5
Triplet	Frozen L	44.29	58.09	32.22	49.58	7.451	23.40	46.40	64.10	45.74	69.68	62.60	68.41	17.95	19.49
Triplet	Both Trainable	61.09	71.37	44.53	61.22	45.71	58.05	56.38	72.85	56.38	78.72	84.84	88.16	26.05	27.94
Triplet	Frozen R	55.89	66.90	37.88	58.52	44.18	56.64	59.05	75.00	55.32	75.00	84.71	88.19	23.45	25.05
MSE	Frozen L	60.08	71.18	27.81	42.50	39.84	56.05	56.61	71.29	39.89	66.49	46.10	52.76	30.67	32.60
MSE	Both Trainable	1.735	6.478	1.183	4.414	2.473	7.173	11.48	23.67	10.11	24.47	0.7218	2.067	1.349	1.606

TABLE V: Ablation study on alignment strategy

Alignment Strategy	Phased-Array 3D Radar (On Average)				Scanning Radar (On Average)				Phased-Array 4D Radar (On Average)
Alignment Strategy	$H(L)$	$H(R)$	LPR (AR@1)	RPR (AR@1)	$H(L)$	$H(R)$	LPR (AR@1)	RPR (AR@1)	$H(L)$	$H(R)$	LPR (AR@1)	RPR (AR@1)
Pre-Alignment	0.9378	1.088	88.26	81.51	1.060	1.184	86.78	88.14	0.9213	0.9670	87.34	78.45
Frozen L	0.9378	1.114	88.26 (-0.00)	81.50 ( -0.01 )	1.060	1.182	86.78 (-0.00)	85.81 ( -2.33 )	0.9213	1.055	87.34 (-0.00)	73.10 ( -5.35 )
Both Trainable	1.215	1.112	81.82 ( -6.44 )	74.00 ( -7.51 )	1.110	1.103	79.58 ( -7.20 )	77.39 ( -10.75 )	1.097	0.9365	82.72 ( -4.62 )	76.91 ( -1.54 )
Frozen R	1.266	1.088	85.41 ( -2.85 )	81.51 (-0.00)	1.156	1.184	85.23 ( -1.55 )	88.14 (-0.00)	1.127	0.9670	83.70 ( -3.64 )	78.45 (-0.00)

TABLE VI: The impact of alignment strategies on modality-specific discriminability

CMP	GAP	CAP	LD	GD	PCE	PCG	BS		SON
CMP	GAP	CAP	LD	GD	PCE	PCG	AR@1	AR@5	AR@1	AR@5
✗	✗	✓	✓	✗	✗	✗	43.21	61.01	8.827	19.56
✗	✗	✗	✗	✓	✗	✗	51.00	69.07	9.341	23.49
✗	✗	✓	✓	✓	✗	✗	64.26	75.70	55.17	71.70
✓	✗	✗	✓	✓	✓	✗	68.21	78.33	49.03	67.71
✗	✓	✗	✓	✓	✓	✗	58.28	72.46	16.44	30.50

TABLE VII: Ablation study on network architecture

Method	Bor-Snow
Method	AR@1	AR@5	AR@10	AR@20	max $F_{1}$
MinkLoc3Dv2 [ 16 ]	18.83	31.63	37.45	43.49	0.4606
BEVPlace++ [ 18 ]	67.31	73.62	76.01	79.49	0.8524
Radar-to-LiDAR [ 31 ]	5.158	24.49	48.46	62.68	0.09880
RaLF [ 21 ]	74.79	86.81	90.65	93.88	0.8588
RLPR (ours)	85.52	93.92	95.86	97.58	0.9226

TABLE VIII: Comparison of performance in snowy scenario

Fig. 5: A comparative visualization of radar-to-radar and LiDAR-to-LiDAR place recognition accuracy.

Fig. 6: Visualization of retrieval results in adverse weather. LPR methods are severely degraded by snow-induced noise, leading to consistent retrieval failures, whereas our proposed R2L method remains robust.

Method	Params	FLOPs	Desc.	Extract	Retrieval	Total
Method	(M)	(G)	Size	(ms)	(ms)	(ms)
Radar-to-LiDAR [ 31 ]	4.3	1.11	4800	2.91	1.16	4.07
RaLF [ 21 ]	3.3	5.32	73728	3.25	21.36	24.61
RLPR (ours)	4.5	0.40	512	2.88	0.05	2.93

TABLE IX: System-level efficiency comparison

Autonomous Driving

Autonomous driving develops vehicles that perceive road scenes, predict interactions, and plan and control safe movement with limited or no human input.

See all 536 papers

4DRaL: Bridging 4D Radar with LiDAR for Place Recognition using Knowledge Distillation
Mar 27, 2026Ningyuan Huang, Zhiheng Li, Zheng FangMillimeter-Wave Radar Knowledge Distillation
The authors are all with the Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China.
Dr-LiSA: Direct Radar-Lidar Scan Alignment for SE(3) Localization
Sep 22, 2026Alex Zhang, Daniil Lisus, Cedric Le Gentil +1LiDAR Localization Map-Based Localization
Robotics Institute, University of Toronto, Canada · Mobile Robotics Lab, ETH Zürich, Switzerland
LRC-WeatherNet: LiDAR, RADAR, and Camera Fusion Network for Real-time Weather-type Classification in Autonomous Driving
Mar 23, 2026Nour Alhuda Albashir, Lars Pernickel, Danial Hamoud +2Autonomous Driving Multimodal Sensor Fusion
Halmstad University, School of Information Technology, Center for Applied Intelligent Systems Research, Halmstad, Sweden

Mar 27, 2026J/K move · Enter open · S save

4DRaL: Bridging 4D Radar with LiDAR for Place Recognition using Knowledge Distillation

Ningyuan Huang, Zhiheng Li, Zheng Fang

The authors are all with the Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China.

Millimeter-Wave Radar Knowledge Distillation

Open paper AskPDF arXiv

Place recognition is crucial for loop closure detection and global localization in robotics. Although mainstream algorithms typically rely on cameras and LiDAR, these sensors are susceptible to adverse weather conditions. Fortunately, the recently developed 4D millimeter-wave radar (4D radar) offers a promising solution for all-weather place recognition. However, the inherent noise and sparsity in 4D radar data significantly limit its performance. Thus, in this paper, we propose a novel framework called 4DRaL that leverages knowledge distillation (KD) to enhance the place recognition performance of 4D radar. Its core is to adopt a high-performance LiDAR-to-LiDAR (L2L) place recognition model as a teacher to guide the training of a 4D radar-to-4D radar (R2R) place recognition model. 4DRaL comprises three key KD modules: a local image enhancement module to handle the sparsity of raw 4D radar points, a feature distribution distillation module that ensures the student model generates more discriminative features, and a response distillation module to maintain consistency in feature space between the teacher and student models. More importantly, 4DRaL can also be trained for 4D radar-to-LiDAR (R2L) place recognition through different module configurations. Experimental results prove that 4DRaL achieves state-of-the-art performance in both R2R and R2L tasks regardless of normal or adverse weather.

Abstract

Autonomous Driving

Explore similar work

4DRaL: Bridging 4D Radar with LiDAR for Place Recognition using Knowledge Distillation

Dr-LiSA: Direct Radar-Lidar Scan Alignment for SE(3) Localization

LRC-WeatherNet: LiDAR, RADAR, and Camera Fusion Network for Real-time Weather-type Classification in Autonomous Driving