Rethinking Unsupervised Cross-modal Flow Estimation: Learning from Decoupled Optimization and Consistency Constraint

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Runmin, Wang, Jialiang, Cao, Si-Yuan, Yu, Zhu, Yu, Junchen, Zhang, Guangyi, Shen, Hui-Liang
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912614845513728
author Zhang, Runmin
Wang, Jialiang
Cao, Si-Yuan
Yu, Zhu
Yu, Junchen
Zhang, Guangyi
Shen, Hui-Liang
author_facet Zhang, Runmin
Wang, Jialiang
Cao, Si-Yuan
Yu, Zhu
Yu, Junchen
Zhang, Guangyi
Shen, Hui-Liang
contents This work presents DCFlow, a novel unsupervised cross-modal flow estimation framework that integrates a decoupled optimization strategy and a cross-modal consistency constraint. Unlike previous approaches that implicitly learn flow estimation solely from appearance similarity, we introduce a decoupled optimization strategy with task-specific supervision to address modality discrepancy and geometric misalignment distinctly. This is achieved by collaboratively training a modality transfer network and a flow estimation network. To enable reliable motion supervision without ground-truth flow, we propose a geometry-aware data synthesis pipeline combined with an outlier-robust loss. Additionally, we introduce a cross-modal consistency constraint to jointly optimize both networks, significantly improving flow prediction accuracy. For evaluation, we construct a comprehensive cross-modal flow benchmark by repurposing public datasets. Experimental results demonstrate that DCFlow can be integrated with various flow estimation networks and achieves state-of-the-art performance among unsupervised approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2509_24423
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Rethinking Unsupervised Cross-modal Flow Estimation: Learning from Decoupled Optimization and Consistency Constraint
Zhang, Runmin
Wang, Jialiang
Cao, Si-Yuan
Yu, Zhu
Yu, Junchen
Zhang, Guangyi
Shen, Hui-Liang
Computer Vision and Pattern Recognition
This work presents DCFlow, a novel unsupervised cross-modal flow estimation framework that integrates a decoupled optimization strategy and a cross-modal consistency constraint. Unlike previous approaches that implicitly learn flow estimation solely from appearance similarity, we introduce a decoupled optimization strategy with task-specific supervision to address modality discrepancy and geometric misalignment distinctly. This is achieved by collaboratively training a modality transfer network and a flow estimation network. To enable reliable motion supervision without ground-truth flow, we propose a geometry-aware data synthesis pipeline combined with an outlier-robust loss. Additionally, we introduce a cross-modal consistency constraint to jointly optimize both networks, significantly improving flow prediction accuracy. For evaluation, we construct a comprehensive cross-modal flow benchmark by repurposing public datasets. Experimental results demonstrate that DCFlow can be integrated with various flow estimation networks and achieves state-of-the-art performance among unsupervised approaches.
title Rethinking Unsupervised Cross-modal Flow Estimation: Learning from Decoupled Optimization and Consistency Constraint
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.24423