Výsledky vyhledávání

Report

InterNet: Unsupervised Cross-modal Homography Estimation Based on Interleaved Modality Transfer and Self-supervised Homography Prediction

Autor: Yu, Junchen, Cao, Si-Yuan, Zhang, Runmin, Zhang, Chenghao, Hu, Jianxin, Yu, Zhu, Yu, Beinan, Shen, Hui-liang

We propose a novel unsupervised cross-modal homography estimation framework, based on interleaved modality transfer and self-supervised homography prediction, named InterNet. InterNet integrates modality transfer and self-supervised homography estima

Externí odkaz: http://arxiv.org/abs/2409.17993

Zobrazit plný text záznamu

Report

SCPNet: Unsupervised Cross-modal Homography Estimation via Intra-modal Self-supervised Learning

Autor: Zhang, Runmin, Ma, Jun, Cao, Si-Yuan, Luo, Lun, Yu, Beinan, Chen, Shu-Jie, Li, Junwei, Shen, Hui-Liang

We propose a novel unsupervised cross-modal homography estimation framework based on intra-modal Self-supervised learning, Correlation, and consistent feature map Projection, namely SCPNet. The concept of intra-modal self-supervised learning is first

Externí odkaz: http://arxiv.org/abs/2407.08148

Zobrazit plný text záznamu

Report

I2P-Rec: Recognizing Images on Large-scale Point Cloud Maps through Bird's Eye View Projections

Autor: Zheng, Shuhang, Li, Yixuan, Yu, Zhu, Yu, Beinan, Cao, Si-Yuan, Wang, Minhang, Xu, Jintao, Ai, Rui, Gu, Weihao, Luo, Lun, Shen, Hui-Liang

Place recognition is an important technique for autonomous cars to achieve full autonomy since it can provide an initial guess to online localization algorithms. Although current methods based on images or point clouds have achieved satisfactory perf

Externí odkaz: http://arxiv.org/abs/2303.01043

Zobrazit plný text záznamu

Report

BEVPlace: Learning LiDAR-based Place Recognition using Bird's Eye View Images

Autor: Luo, Lun, Zheng, Shuhang, Li, Yixuan, Fan, Yongzhi, Yu, Beinan, Cao, Siyuan, Shen, Huiliang

Place recognition is a key module for long-term SLAM systems. Current LiDAR-based place recognition methods usually use representations of point clouds such as unordered points or range images. These methods achieve high recall rates of retrieval, bu

Externí odkaz: http://arxiv.org/abs/2302.14325

Zobrazit plný text záznamu

Report

PCNet: A Structure Similarity Enhancement Method for Multispectral and Multimodal Image Registration

Autor: Cao, Si-Yuan, Yu, Beinan, Luo, Lun, Chen, Shu-Jie, Li, Chunguang, Shen, Hui-Liang

Multispectral and multimodal images are of important usage in the field of multi-source visual information fusion. Due to the alternation or movement of image devices, the acquired multispectral and multimodal images are usually misaligned, and hence

Externí odkaz: http://arxiv.org/abs/2106.05124

Zobrazit plný text záznamu