Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2409.05531 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913578520412160 |
|---|---|
| author | Ma, Dianbo Imamura, Kousuke Gao, Ziyan Wang, Xiangjie Yamane, Satoshi |
| author_facet | Ma, Dianbo Imamura, Kousuke Gao, Ziyan Wang, Xiangjie Yamane, Satoshi |
| contents | Optical flow estimation is a fundamental and long-standing visual task. In this work, we present a novel method, dubbed HMAFlow, to improve optical flow estimation in challenging scenes, particularly those involving small objects. The proposed model mainly consists of two core components: a Hierarchical Motion Field Alignment (HMA) module and a Correlation Self-Attention (CSA) module. In addition, we rebuild 4D cost volumes by employing a Multi-Scale Correlation Search (MCS) layer and replacing average pooling in common cost volumes with a search strategy utilizing multiple search ranges. Experimental results demonstrate that our model achieves the best generalization performance compared to other state-of-the-art methods. Specifically, compared with RAFT, our method achieves relative error reductions of 14.2% and 3.4% on the clean pass and final pass of the Sintel online benchmark, respectively. On the KITTI test benchmark, HMAFlow surpasses RAFT and GMA in the Fl-all metric by relative margins of 6.8% and 7.7%, respectively. To facilitate future research, our code will be made available at https://github.com/BooTurbo/HMAFlow. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_05531 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | HMAFlow: Learning More Accurate Optical Flow via Hierarchical Motion Field Alignment Ma, Dianbo Imamura, Kousuke Gao, Ziyan Wang, Xiangjie Yamane, Satoshi Computer Vision and Pattern Recognition Artificial Intelligence Optical flow estimation is a fundamental and long-standing visual task. In this work, we present a novel method, dubbed HMAFlow, to improve optical flow estimation in challenging scenes, particularly those involving small objects. The proposed model mainly consists of two core components: a Hierarchical Motion Field Alignment (HMA) module and a Correlation Self-Attention (CSA) module. In addition, we rebuild 4D cost volumes by employing a Multi-Scale Correlation Search (MCS) layer and replacing average pooling in common cost volumes with a search strategy utilizing multiple search ranges. Experimental results demonstrate that our model achieves the best generalization performance compared to other state-of-the-art methods. Specifically, compared with RAFT, our method achieves relative error reductions of 14.2% and 3.4% on the clean pass and final pass of the Sintel online benchmark, respectively. On the KITTI test benchmark, HMAFlow surpasses RAFT and GMA in the Fl-all metric by relative margins of 6.8% and 7.7%, respectively. To facilitate future research, our code will be made available at https://github.com/BooTurbo/HMAFlow. |
| title | HMAFlow: Learning More Accurate Optical Flow via Hierarchical Motion Field Alignment |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2409.05531 |