EUVIMEDEUVIMED entdecken
Crossref

DeMatch++: Two-View Correspondence Learning via Deep Motion Field Decomposition and Respective Local-Context Aggregation

Shihua Zhang, Zizhuo Li, Jiayi Ma

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-12 · 47 (12) · 11234-11251

DOI: 10.1109/tpami.2025.3596598 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-12. Verfasst von Shihua Zhang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 94 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Two-view correspondence learning has increasingly focused on the coherence and smoothness of motion fields between image pairs. Conventional methods either regularize the complexity of the field function at substantial computational expense, or apply local filters that prove ineffective for large scene disparities. In this paper, we present DeMatch++, a novel network drawing inspiration from Fourier decomposition principles that decomposes the motion field to retain its primary "low-frequency" and smooth components. This approach achieves implicit regularization with lower computational overhead while exhibiting inherent piecewise smoothness. Specifically, our method decomposes the noise-contaminated motion field into multiple linearly independent basis vectors, generating smooth sub-fields that preserve the main energy of the original field. These sub-fields facilitate the recovery of a cleaner motion field for precise vector derivation. Within this framework, we aggregate local context within each sub-field while enhancing global information across all sub-fields. We also employ a masked decomposition strategy that mitigates the influence of false matches, and construct a compact representation to suppress redundant sub-fields. The complete pipeline is formulated as a discrete learnable architecture, circumventing the need for dense field computation. Extensive experiments demonstrate that DeMatch++ outperforms state-of-the-art methods while maintaining computational efficiency and piecewise smoothness.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Zhang, S., Li, Z., & Ma, J. (2025). DeMatch++: Two-View Correspondence Learning via Deep Motion Field Decomposition and Respective Local-Context Aggregation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(12), 11234-11251. https://doi.org/10.1109/tpami.2025.3596598

Vancouver

Zhang S, Li Z, Ma J. DeMatch++: Two-View Correspondence Learning via Deep Motion Field Decomposition and Respective Local-Context Aggregation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(12):11234-11251. doi:10.1109/tpami.2025.3596598

BibTeX
@article{Zhang2025,
  author = {Zhang, Shihua and Li, Zizhuo and Ma, Jiayi},
  title = {DeMatch++: Two-View Correspondence Learning via Deep Motion Field Decomposition and Respective Local-Context Aggregation},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {12},
  pages = {11234--11251},
  doi = {10.1109/tpami.2025.3596598}
}
Kostenlos starten →