paper-with-me

Papers

Self-Supervised Cross-Modal Learning for Image-to-Point Cloud Registration

2025-09-19 · Xingmei Wang, Xiaoyu Hu, Chengkai Huang, Ziyan Zeng, Guohao Nie, Quan Z. Sheng, Lina Yao arxiv

Bridging 2D and 3D sensor modalities is critical for robust perception in autonomous systems. However, image-to-point cloud (I2P) registration remains challenging due to the semantic-geometric gap between texture-rich but depth-ambiguous images and sparse yet metrically precise point clouds, as well as the tendency of existing methods to converge to local optima. To overcome these limitations, we introduce CrossI2P, a self-supervised framework that unifies cross-modal learning and two-stage registration in a single end-to-end pipeline. First, we learn a geometric-semantic fused embedding space via dual-path contrastive learning, enabling annotation-free, bidirectional alignment of 2D textures and 3D structures. Second, we adopt a coarse-to-fine registration paradigm: a global stage establishes superpoint-superpixel correspondences through joint intra-modal context and cross-modal interaction modeling, followed by a geometry-constrained point-level refinement for precise registration. Third, we employ a dynamic training mechanism with gradient normalization to balance losses for feature alignment, correspondence refinement, and pose estimation. Extensive experiments demonstrate that CrossI2P outperforms state-of-the-art methods by 23.7% on the KITTI Odometry benchmark and by 37.9% on nuScenes, significantly improving both accuracy and robustness.

📄 PDF Abstract BibTeX arXiv:2509.15882

Code (0)

등록된 구현이 없습니다.

Tasks

Point Cloud RegistrationContrastive LearningPose EstimationPoint Clouds

Similar Papers 제목 키워드 기반

PointCMC: Cross-Modal Multi-Scale Correspondences Learning for Point Cloud Understanding

2022-11-22 · Honggu Zhou, Xiaogang Peng, Jiawei Mao, Zizhao Wu 외

Some self-supervised cross-modal learning approaches have recently demonstrated the potential of image signals for enhancing point cloud representation. However, it remains a question on how to directly model cross-modal…

3D Object ClassificationRepresentation Learning

CrossVideo: Self-supervised Cross-modal Contrastive Learning for Point Cloud Video Understanding

2024-01-17 · Yunze Liu, Changxi Chen, Zifan Wang, Li Yi

This paper introduces a novel approach named CrossVideo, which aims to enhance self-supervised cross-modal contrastive learning in the field of point cloud video understanding. Traditional supervised learning methods enc…

Contrastive Learningpoint cloud video understandingSelf-Supervised LearningVideo Understanding

CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding

2022-03-01 · CVPR 2022 1 · Mohamed Afham, Isuru Dissanayake, Dinithi Dissanayake, Amaya Dharmasiri 외

Manual annotation of large-scale point cloud dataset for varying tasks such as 3D object classification, segmentation and detection is often laborious owing to the irregular structure of point clouds. Self-supervised lea…

3D Object Classification3D Point Cloud Linear ClassificationContrastive LearningFew-Shot 3D Point Cloud Classification+1

Self-Supervised Modality-Invariant and Modality-Specific Feature Learning for 3D Objects

2021-09-29 · Longlong Jing, Zhimin Chen, Bing Li, YingLi Tian

While most existing self-supervised 3D feature learning methods mainly focus on point cloud data, this paper explores the inherent multimodal attributes of 3D objects. We propose to jointly learn effective features from …

3D Object RecognitionCross-Modal RetrievalObject RecognitionRetrieval

Self-supervised Feature Learning by Cross-modality and Cross-view Correspondences

2020-04-13 · Longlong Jing, Yu-cheng Chen, Ling Zhang, Mingyi He 외

The success of supervised learning requires large-scale ground truth labels which are very expensive, time-consuming, or may need special skills to annotate. To address this issue, many self- or un-supervised methods are…

3D Part Segmentation3D Shape Classification3D Shape Recognition3D Shape Retrieval+2