SSHNet: Unsupervised Cross-modal Homography Estimation via Problem Reformulation and Split Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912348188442624 |
|---|---|
| author | Yu, Junchen Cao, Si-Yuan Zhang, Runmin Zhang, Chenghao Yu, Zhu Chen, Shujie Yang, Bailin Shen, Hui-liang |
| author_facet | Yu, Junchen Cao, Si-Yuan Zhang, Runmin Zhang, Chenghao Yu, Zhu Chen, Shujie Yang, Bailin Shen, Hui-liang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_17993 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SSHNet: Unsupervised Cross-modal Homography Estimation via Problem Reformulation and Split Optimization Yu, Junchen Cao, Si-Yuan Zhang, Runmin Zhang, Chenghao Yu, Zhu Chen, Shujie Yang, Bailin Shen, Hui-liang Computer Vision and Pattern Recognition 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. |
| title | SSHNet: Unsupervised Cross-modal Homography Estimation via Problem Reformulation and Split Optimization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.17993 |