CMHANet: A Cross-Modal Hybrid Attention Network for Point Cloud Registration

Dongxu Zhang; Yingsen Wang; Yiding Sun; Haoran Xu; Peilin Fan; Jihua Zhu

cs.CVMar 13, 2026

CMHANet: A Cross-Modal Hybrid Attention Network for Point Cloud Registration

Authors: Dongxu Zhang, Yingsen Wang, Yiding Sun, Haoran Xu, Peilin Fan, Jihua Zhu

Organizations: School of Software, Xi’an Jiaotong University, No. 28 Xianning West Road, China · CEPRI, China Electric Power Research Institute No. 15 Xiaoying East Road, Qinghe, Haidian District, Beijing, China

Abstract

Robust point cloud registration is a fundamental task in 3D computer vision and geometric deep learning, essential for applications such as large-scale 3D reconstruction, augmented reality, and scene understanding. However, the performance of established learning-based methods often degrades in complex, real world scenarios characterized by incomplete data, sensor noise, and low overlap regions. To address these limitations, we propose CMHANet, a novel Cross-Modal Hybrid Attention Network. Our method integrates the fusion of rich contextual information from 2D images with the geometric detail of 3D point clouds, yielding a comprehensive and resilient feature representation. Furthermore, we introduce an innovative optimization function based on contrastive learning, which enforces geometric consistency and significantly improves the model's robustness to noise and partial observations. We evaluated CMHANet on the 3DMatch and the challenging 3DLoMatch datasets. \rev{Additionally, zero-shot evaluations on the TUM RGB-D SLAM dataset verify the model's generalization capability to unseen domains.} The experimental results demonstrate that our method achieves substantial improvements in both registration accuracy and overall robustness, outperforming current techniques. We also release our code in https://github.com/DongXu-Zhang/CMHANet.

Figures & tables

Figure 1: The pixel-to-point correspondence between the point cloud and the image has been established by external parameter calibration, so this method is reasonable, and can effectively combine the global texture features of the image with the local geometric characteristics of the point cloud.

Figure 2: The Registration Recall (RR) is plotted on the x-axis for 3DMatch and on the y-axis for 3DLoMatch. CMHANet stands out by consistently achieving the highest RR.

Figure 3: The workflow overview of CMHANet. Our method processes raw point clouds and images through feature extraction, employs a hybrid-attention mechanism for superpoint matching, refines to dense point correspondences, and finally computes the rigid transformation for alignment.

Figure 4: Details of the superpoint matching module. This module employs a multi-stage attention mechanism: Self-Attention refines individual modality features, followed by Aggregation-Attention for structured intra-modal feature integration, and finally Cross-Attention to fuse features across modalities, ultimately generating a similarity matrix for robust superpoint matching. For visualization, the blue blocks represent the source point cloud features (

\hat{F}^{P}

), the orange blocks represent the target point cloud features (

\hat{F}^{Q}

), and the yellow lines indicate the attention interactions.

Figure 5: Computation graph of the Hybrid Attention mechanism. In the diagrams, the label

F

denotes feature representations (

e.g.,

\hat{F}^{PC}

for generic point cloud features,

\hat{F}^{P}

and

\hat{F}^{Q}

for source and target point cloud features (in a, c),

\hat{F}^{I}

for image features), and

E

represents geometric positional embeddings. The three modules serve distinct roles. (a) Geometric Self-Attention captures global structural relationships within a single point cloud; (b) Geometric Aggregation-Attention fuses 2D visual context from images into 3D geometric features; and (c) Geometric Cross-Attention establishes consistency and searches for correspondences between the source and target point clouds.

Feature Matching Recall (%) $\uparrow$
	3DMatch					3DLoMatch
# Samples	5000	2500	1000	500	250	5000	2500	1000	500	250
PerfectMatch [ 18 ]	95.0	94.3	92.9	90.1	82.9	63.6	61.7	53.6	45.2	34.2
FCGF [ 13 ]	97.4	97.3	97.0	96.7	96.6	76.6	75.4	74.2	71.7	67.3
D3Feat [ 5 ]	95.6	94.3	95.6	94.3	91.0	66.7	64.7	61.6	60.0	56.6
SpinNet [ 3 ]	97.6	97.2	96.8	95.5	96.5	75.3	74.9	72.5	70.0	63.6

Table 1: Evaluation results of our method on 3DMatch and 3DLoMatch datasets. The results are reported for two key metrics: Feature Matching Recall (%) and Registration Recall (%). The evaluation is conducted across varying sample sizes (5000, 2500, 1000, 500 and 250) to assess the robustness of each method under different constraints.

Model	Estimator	3DMatch		3DLoMatch
Model	Estimator	RRE (°)	RTE (m)	RRE (°)	RTE (m)
Predator [ 25 ]	RANSAC- 50k	2.029	0.064	3.048	0.093
CoFiNet [ 60 ]	RANSAC- 50k	2.002	0.064	3.271	0.090
PCR-CG [ 70 ]	RANSAC- 50k	1.993	0.061	3.002	0.087
MAC [ 69 ]	RANSAC-free	2.003	0.065	3.010	0.085
Hybrid [ 27 ]	RANSAC-free	1.992	0.061	3.002	0.087

Table 2: RRE and RTE on 3DMatch (3DM) and 3DLoMatch (3DLM) benchmarks. We report Relative Rotation Error (RRE, °) and Relative Translation Error (RTE, m) for various methods using RANSAC-50k or RANSAC-free estimators. CMHANet achieves the lowest RRE and RTE on both datasets.

Model	3DMatch		3DLoMatch
Model	FMR	RR	FMR	RR
IMFNet [ 26 ]	98.5	91.0	80.5	48.4
PCR-CG [ 70 ]	97.4	89.4	80.4	66.3
CMHANet ( ours )	98.6	92.4	87.7	75.5

Table 3: Comparison With Multimodal Point Cloud Registration

Model	Estimator	# Samples	RR (%)		Times (s)
Model	Estimator	# Samples	3DM	3DLM	Model	Pose	Total
FCGF [ 13 ]	RANSAC-50k	5000	85.1	40.1	0.052	3.326	3.378
D3Feat [ 5 ]	RANSAC-50k	5000	81.6	37.2	0.024	3.088	3.112
SpinNet [ 3 ]	RANSAC-50k	5000	88.6	59.8	0.248	0.388	60.636
Predator [ 25 ]	RANSAC-50k	5000	89.0	59.8	0.032	5.120	5.152
CoFiNet [ 60 ]	RANSAC-50k	5000	89.3	67.5	0.115	1.807	1.922

Table 4: Comparison of Model Registration Performance with Different Estimators and Sample sizes On 3DMatch(3DM) and 3DLomatch(3DLM). We report Registration Recall (RR, %) and computation times (Model, Pose, and Total, in seconds) for various methods. Evaluations are conducted with RANSAC-50k, Weighted SVD, and LGR to assess robustness and efficiency. CMHANet consistently achieves superior performance in both metrics.

Figure 6: The result of CMHANet. We visualized representative scenes from the 3DMatch dataset. The first row shows the initial arrangement of the two point clouds in their raw, unaligned positions. The middle row depicts the ground truth alignment of the two point clouds, representing the ideal registration outcome. The bottom row showcases the registration results predicted by CMHANet, offering a direct comparison to both the initial misalignment and the ground truth. We also report the Root Mean Square Error (RMSE) values for each scene, quantifying the spatial deviation between CMHANet’s predicted alignments and the ground truth.

Method	xyz	360	teddy	desk	plant	dishes	coke	flower	mean
ICP [ 6 ]	2.1	5.1	2.1	2.3	1.6	3.7	3.1	2.7	2.8
AA-ICP [ 34 ]	2.1	5.1	2.1	2.3	1.6	3.7	3.1	2.7	2.8
Sparse ICP [ 7 ]	1.6	4.8	1.8	1.8	0.88	3.9	3.3	3.2	2.66
Robust ICP [ 68 ]	0.5	2.2	1	1.2	0.65	3.2	2.4	2.4	1.69
Teaser++ [ 57 ]	3.4	20	11	8	6.1	21	23	20	14.06
DCP [ 51 ]	6.5	10	6.6	7	5.6	7.4	7.5	6.3	7.11

Table 5: Registration Results on Eight Sequences from the TUM RGB-D SLAM Dataset. We report the Average RMSE (

\times 10^{-2}

). Our method (CMHANet) is trained on 3DMatch and directly tested on TUM without fine-tuning.

Module			3DMatch				3DLoMatch
Loss	HA	IM	PIR	FMR	IR	RR	PIR	FMR	IR	RR
$\checkmark$	-	-	83.8	97.4	68.2	89.9	50.9	86.0	41.2	71.9
-	-	$\checkmark$	84.2	97.8	65.9	90.1	51.2	86.3	40.8	72.1
-	$\checkmark$	$\checkmark$	85.1	98.5	69.2	91.4	51.7	86.8	42.9	74.2
$\checkmark$	-	$\checkmark$	84.0	98.2	68.8	90.5	52.2	86.5	41.8	72.4
$\checkmark$	$\checkmark$	$\checkmark$	86.8	98.6	70.7	92.4	54.8	87.7	43.1	75.5

Table 6: Ablation experiments of the CMHANet. The results are measured in %. We also assess the impact of including (

\checkmark

) or excluding (-) our custom Loss function, Hybrid Attention (HA) module, and Image Module (IM) on PIR, FMR, IR, and RR metrics. Best performance is highlighted in bold.

Model	3DMatch				3DLoMatch
Model	PIR	FMR	IR	RR	PIR	FMR	IR	RR
w/o IM Module	83.8	97.4	68.2	89.9	50.9	86.0	41.2	71.9
Resnet-34	84.9	97.8	68.7	90.9	51.2	86.3	41.8	73.1
Resnet-101	87.0	98.5	71.2	92.4	54.7	87.2	42.9	75.2
CMHANet	86.8	98.6	70.7	92.4	54.8	87.7	43.1	75.5

Table 7: Ablation Experiments on Image Module in CMHANet. Best performance is highlighted in bold. The second-best performance results are indicated by underlines.

Model	3DMatch				3DLoMatch
Model	PIR	FMR	IR	RR	PIR	FMR	IR	RR
w/o HA Module	84.0	98.2	68.8	90.5	52.2	86.5	41.8	72.4
w/o Aggre Att	85.9	98.3	70.2	91.3	53.7	86.7	42.8	73.6
CMHANet	86.8	98.6	70.7	92.4	54.8	87.7	43.1	75.5

Table 8: Ablation Experiments on Hybrid Attention Module in CMHANet. Best performance is highlighted in bold.

Figure 7: Visual ablation comparison demonstrating the impact of different feature transformation modules on registration performance. From left to right, w/o IM: Without the Image Module, the network relies solely on geometry; w/o HA: Removing the Hybrid Attention module hinders effective global feature interaction; CMHANet: Our full model leverages cross-modal feature transformation; Ground Truth: Shown for reference.

Explore similar work

IGASA: Integrated Geometry-Aware and Skip-Attention Modules for Enhanced Point Cloud Registration
Mar 13, 2026Dongxu Zhang, Jihua Zhu, Shiqi Li +4Point Cloud Registration Point Cloud Learning
C-GenReg: Training-Free 3D Point Cloud Registration by Multi-View-Consistent Geometry-to-Image Generation with Probabilistic Modalities Fusion
Apr 17, 2026Yuval Haitman, Amit Efraim, Joseph M. FrancosPoint Cloud Registration Cross-Modal Feature Matching
Ben-Gurion University, Beer-Sheva, Israel
GLASS: Geometry-aware Local Alignment and Structure Synchronization Network for 2D-3D Registration
Mar 27, 2026Zhixin Cheng, Jiacheng Deng, Xinjun Li +5Point Cloud Registration Cross-Modal Image Registration
School of Information Science and Technology, University of Science and Technology of China, Hefei 230027, China · Meituan Inc, Beijing 100000, China · Institute of Advanced Technology, University of Science and Technology of China, Hefei 230027, China

Mar 13, 2026J/K move · Enter open · S save

IGASA: Integrated Geometry-Aware and Skip-Attention Modules for Enhanced Point Cloud Registration

Dongxu Zhang, Jihua Zhu, Shiqi Li, Wenbiao Yan+3

Point Cloud Registration Point Cloud Learning Attention Mechanisms

Open paper AskPDF arXiv

Point cloud registration (PCR) is a fundamental task in 3D vision and provides essential support for applications such as autonomous driving, robotics, and environmental modeling. Despite its widespread use, existing methods often fail when facing real-world challenges like heavy noise, significant occlusions, and large-scale transformations. These limitations frequently result in compromised registration accuracy and insufficient robustness in complex environments. In this paper, we propose IGASA as a novel registration framework constructed upon a Hierarchical Pyramid Architecture (HPA) designed for robust multi-scale feature extraction and fusion. The framework integrates two pivotal components consisting of the Hierarchical Cross-Layer Attention (HCLA) module and the Iterative Geometry-Aware Refinement (IGAR) module. The HCLA module utilizes skip attention mechanisms to align multi-resolution features and enhance local geometric consistency. Simultaneously, the IGAR module is designed for the fine matching phase by leveraging reliable correspondences established during coarse matching. This synergistic integration within the architecture allows IGASA to adapt effectively to diverse point cloud structures and intricate transformations. We evaluate the performance of IGASA on four widely recognized benchmark datasets including 3D(Lo)Match, KITTI, and nuScenes. Our extensive experiments consistently demonstrate that IGASA significantly surpasses state-of-the-art methods and achieves notable improvements in registration accuracy. This work provides a robust foundation for advancing point cloud registration techniques while offering valuable insights for practical 3D vision applications. The code for IGASA is available in https://github.com/DongXu-Zhang/IGASA.

Abstract

Explore similar work

IGASA: Integrated Geometry-Aware and Skip-Attention Modules for Enhanced Point Cloud Registration

C-GenReg: Training-Free 3D Point Cloud Registration by Multi-View-Consistent Geometry-to-Image Generation with Probabilistic Modalities Fusion

GLASS: Geometry-aware Local Alignment and Structure Synchronization Network for 2D-3D Registration