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

• URL: http://arxiv.org/abs/2603.12721v1
• Date: Fri, 13 Mar 2026 07:09:22 GMT
• Title: CMHANet: A Cross-Modal Hybrid Attention Network for Point Cloud Registration
• Abstract summary: We propose CMHANet, a novel Cross-Modal Hybrid Attention Network.<n>Our method integrates the fusion of rich contextual information from 2D images with the geometric detail of 3D point clouds.<n>We show that our method achieves substantial improvements in both registration accuracy and overall robustness, outperforming current techniques.
• Score: 26.457061044468915
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 \href{https://github.com/DongXu-Zhang/CMHANet}{https://github.com/DongXu-Zhang/CMHANet}.

Related papers

• xModel-KD: Cross-modal Knowledge Distillation for 3D Scene Perception using LiDAR [1.0055428846517074]
  We propose a novel cross-modal knowledge distillation framework, xModel-KD, for 3D point cloud segmentation.<n>Our method exploits the complementary strengths of 2D texture and 3D geometry by learning unified per-point representations.<n> Experimental results show that cross-modal fusion achieves a 2% absolute improvement in mIoU over a LiDAR-only baseline.
  arXiv  Detail & Related papers  (2026-05-28T15:48:38Z)
• MASt3R-Fusion: Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM [12.158063913401575]
  We propose MASt3R-Fusion, a multi-sensor-assisted visual SLAM framework that integrates feed-forward pointmap regression with complementary sensor information.<n>A hierarchical factor graph design is developed, which allows both real-time sliding-window optimization and global optimization with aggressive loop closures.<n>We evaluate our approach on both public benchmarks and self-collected datasets, demonstrating substantial improvements in accuracy and robustness.
  arXiv  Detail & Related papers  (2025-09-25T05:26:28Z)
• No Need for Real 3D: Fusing 2D Vision with Pseudo 3D Representations for Robotic Manipulation Learning [4.857549394680453]
  NoReal3D: which introduces the 3DStructureFormer, a learnable 3D perception module capable of transforming monocular images into geometrically meaningful pseudo-point cloud features.<n>Our framework enhances the robot's understanding of 3D spatial structures while completely eliminating the substantial costs associated with 3D point cloud acquisition.
  arXiv  Detail & Related papers  (2025-09-20T04:43:42Z)
• TriCLIP-3D: A Unified Parameter-Efficient Framework for Tri-Modal 3D Visual Grounding based on CLIP [52.79100775328595]
  3D visual grounding allows an embodied agent to understand visual information in real-world 3D environments based on human instructions.<n>Existing 3D visual grounding methods rely on separate encoders for different modalities.<n>We propose a unified 2D pre-trained multi-modal network to process all three modalities.
  arXiv  Detail & Related papers  (2025-07-20T10:28:06Z)
• Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognition [63.55828203989405]
  We introduce a novel Topology-Aware Modeling (TAM) framework for Sim2Real UDA on object point clouds.<n>Our approach mitigates the domain gap by leveraging global spatial topology, characterized by low-level, high-frequency 3D structures.<n>We propose an advanced self-training strategy that combines cross-domain contrastive learning with self-training.
  arXiv  Detail & Related papers  (2025-06-26T11:53:59Z)
• GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistency [50.11520458252128]
  Existing 3D affordance learning methods struggle with generalization and robustness due to limited annotated data.<n>We propose GEAL, a novel framework designed to enhance the generalization and robustness of 3D affordance learning by leveraging large-scale pre-trained 2D models.<n>GEAL consistently outperforms existing methods across seen and novel object categories, as well as corrupted data.
  arXiv  Detail & Related papers  (2024-12-12T17:59:03Z)
• DeCoTR: Enhancing Depth Completion with 2D and 3D Attentions [41.55908366474901]
  We introduce a novel approach that harnesses both 2D and 3D attentions to enable highly accurate depth completion. We evaluate our method, DeCoTR, on established depth completion benchmarks.
  arXiv  Detail & Related papers  (2024-03-18T19:22:55Z)
• FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models [59.13757801286343]
  Few-shot class-incremental learning aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data.<n>We introduce the FILP-3D framework with two novel components: the Redundant Feature Eliminator (RFE) for feature space misalignment and the Spatial Noise Compensator (SNC) for significant noise.
  arXiv  Detail & Related papers  (2023-12-28T14:52:07Z)
• AGO-Net: Association-Guided 3D Point Cloud Object Detection Network [86.10213302724085]
  We propose a novel 3D detection framework that associates intact features for objects via domain adaptation. We achieve new state-of-the-art performance on the KITTI 3D detection benchmark in both accuracy and speed.
  arXiv  Detail & Related papers  (2022-08-24T16:54:38Z)
• Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception [122.53774221136193]
  State-of-the-art methods for driving-scene LiDAR-based perception often project the point clouds to 2D space and then process them via 2D convolution. A natural remedy is to utilize the 3D voxelization and 3D convolution network. We propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pattern.
  arXiv  Detail & Related papers  (2021-09-12T06:25:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.