EUVIMEDEUVIMED entdecken
Crossref

Seam-Guided Unsupervised Image Stitching With Parallax-Aware Mask Generation

Yuzhu Tao, Lang Nie, Yakun Chang, Bo Li, Qingwen Li, Hong Li, Shikui Wei

IEEE Transactions on Circuits and Systems for Video Technology · 2026-07 · 36 (7) · 10824-10835

DOI: 10.1109/tcsvt.2026.3671350 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-07. Verfasst von Yuzhu Tao und 6 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben. Gefördert von: National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image stitching under large parallax remains a challenging task due to the conflict of content alignment and shape preservation. Most methods focus on precisely aligning overlapping regions via spatially varying transformations, often causing unexpected distortions in large-parallax areas. Differently, we aim to produce stitched images that are both visually natural and free of artifacts. To this end, we present a parallax-aware unsupervised warping model for seam-guided image stitching. To preserve natural content, we first design an edge-enhanced mask generation module to distinguish large-parallax regions and suppress excessive deformation around these areas. It is constrained by a comprehensive objective function that integrates masked photometric difference, nontrivial mask learning, and adaptive regularization, simultaneously ensuring mask reliability and alignment robustness. Besides, to eliminate parallax artifacts, we incorporate a seam-guided alignment strategy into our warping network, which iteratively registers local regions with the assistance of optimal seam estimation. Through adaptively finetuning the warping model, we progressively improve the stitching quality with improved seam quality. To facilitate the learning process of perceiving parallax, we construct a new image stitching dataset with larger parallax than that of UDIS-D, which could benefit the model’s generalization in challenging scenarios. Experiments show our solution not only removes misaligned regions but also maintains shape consistency especially in challenging parallax scenarios.

Förderung

  • National Key Research and Development Program of China

Zitieren

APA

Tao, Y., Nie, L., Chang, Y., Li, B., Li, Q., Li, H., & Wei, S. (2026). Seam-Guided Unsupervised Image Stitching With Parallax-Aware Mask Generation. IEEE Transactions on Circuits and Systems for Video Technology, 36(7), 10824-10835. https://doi.org/10.1109/tcsvt.2026.3671350

Vancouver

Tao Y, Nie L, Chang Y, Li B, Li Q, Li H, et al. Seam-Guided Unsupervised Image Stitching With Parallax-Aware Mask Generation. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(7):10824-10835. doi:10.1109/tcsvt.2026.3671350

BibTeX
@article{Tao2026,
  author = {Tao, Yuzhu and Nie, Lang and Chang, Yakun and Li, Bo and Li, Qingwen and Li, Hong and Wei, Shikui},
  title = {Seam-Guided Unsupervised Image Stitching With Parallax-Aware Mask Generation},
  journal = {IEEE Transactions on Circuits and Systems for Video Technology},
  year = {2026},
  volume = {36},
  number = {7},
  pages = {10824--10835},
  doi = {10.1109/tcsvt.2026.3671350}
}
Kostenlos starten →