Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ma, Dianbo, Imamura, Kousuke, Gao, Ziyan, Wang, Xiangjie, Yamane, Satoshi
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