arXiv 2409.179932025-04-27cs.CV

SSHNet：基于问题重构与分裂优化的无监督跨模态单应性估计

SSHNet: Unsupervised Cross-modal Homography Estimation via Problem Reformulation and Split Optimization

Ningbo Innovation Center, Zhejiang University（浙江大学宁波创新中心）；College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）；NingboTech University（宁波科技学院）；Zhejiang Key Laboratory of Big Data and Future ECommerce Technology, Hangzhou, China（浙江大数据与未来电子商务技术重点实验室）

Junchen Yu, Si-Yuan Cao, Runmin Zhang, Chenghao Zhang, Zhu Yu, Shujie Chen, Bailin Yang, Hui-liang Shen

备注：: Accepted by CVPR 2025

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出无监督跨模态单应性估计框架SSHNet，通过将问题重构为模态迁移与单应性估计两个子问题并采用分裂优化策略稳定训练，辅以特征监督和蒸馏技术，在OPT-SAR数据集上超越现有无监督方法并优于部分有监督方法。

摘要：

我们提出了一种新颖的无监督跨模态单应性估计学习框架，名为分裂监督单应性估计网络（SSHNet）。SSHNet将无监督跨模态单应性估计重构为两个有监督子问题，每个子问题由其专用网络解决：单应性估计网络和模态迁移网络。为实现稳定训练，我们引入了一种有效的分裂优化策略，在各自子问题中分别训练每个网络。我们还构建了额外的单应性特征空间监督以增强特征一致性，进一步提升估计精度。此外，我们采用了一种简单有效的蒸馏训练技术来减少模型参数并改善跨域泛化能力，同时保持可比的性能。SSHNet的训练稳定性使其能与各种单应性估计架构协同工作。实验表明，使用IHN作为单应性估计网络的SSHNet，即SSHNet-IHN，以显著优势超越了以往的无监督方法。即使与有监督方法MHN和LocalTrans相比，SSHNet-IHN在具有挑战性的OPT-SAR数据集上也实现了47.4%和85.8%的平均角点误差（MACEs）降低。

英文摘要：

We propose a novel unsupervised cross-modal homography estimation learning framework, named Split Supervised Homography estimation Network (SSHNet). SSHNet reformulates the unsupervised cross-modal homography estimation into two supervised sub-problems, each addressed by its specialized network: a homography estimation network and a modality transfer network. To realize stable training, we introduce an effective split optimization strategy to train each network separately within its respective sub-problem. We also formulate an extra homography feature space supervision to enhance feature consistency, further boosting the estimation accuracy. Moreover, we employ a simple yet effective distillation training technique to reduce model parameters and improve cross-domain generalization ability while maintaining comparable performance. The training stability of SSHNet enables its cooperation with various homography estimation architectures. Experiments reveal that the SSHNet using IHN as homography estimation network, namely SSHNet-IHN, outperforms previous unsupervised approaches by a significant margin. Even compared to supervised approaches MHN and LocalTrans, SSHNet-IHN achieves 47.4% and 85.8% mean average corner errors (MACEs) reduction on the challenging OPT-SAR dataset.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。