EUVIMEDEUVIMED entdecken
Crossref

Self-supervised migration image restoration constrained by spatially variant point-spread functions

Jingwen Zeng, Hao Wang, Yingzhe Bai, Lu Xu

Journal of Seismic Exploration · 29.10.2026 · 026260115

DOI: 10.36922/jse026260115 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Seismic Exploration, online erschienen am 29.10.2026. Verfasst von Jingwen Zeng und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Least-squares migration can improve image resolution and compensate for uneven illumination, but data-domain implementations require repeated modeling and migration. Image-domain methods based on point-spread functions (PSFs) reduce this cost by approximating the local Hessian response, yet their performance depends on the representativeness of local PSFs in structurally complex areas. We propose SPIRE-Net, a self-supervised migration image restoration framework constrained by spatially variant PSFs. The network predicts a restored image patch, which is then filtered by the PSF assigned to the corresponding spatial location. Training minimizes the mismatch between this PSF-filtered prediction and the input image patch without requiring supervised target images. Structure-aware adaptive PSF-paired sampling and a structure-enhanced consistency loss strengthen the constraint in complex structural regions. The Marmousi experiment demonstrates the ability of SPIRE-Net to solve the prescribed PSF-based image-domain inverse problem through self-supervised learning. Field-data comparisons show improved local reflector continuity and event separation relative to image-domain LSM in the examined regions, while preserving the main reflection geometry. These results suggest that spatially variant PSFs can serve as physical constraints for self-supervised migration image restoration.

Zitieren

APA

Zeng, J., Wang, H., Bai, Y., & Xu, L. (2026). Self-supervised migration image restoration constrained by spatially variant point-spread functions. Journal of Seismic Exploration, 0(0), 026260115. https://doi.org/10.36922/jse026260115

Vancouver

Zeng J, Wang H, Bai Y, Xu L. Self-supervised migration image restoration constrained by spatially variant point-spread functions. Journal of Seismic Exploration. 2026;0(0):026260115. doi:10.36922/jse026260115

BibTeX
@article{Zeng2026,
  author = {Zeng, Jingwen and Wang, Hao and Bai, Yingzhe and Xu, Lu},
  title = {Self-supervised migration image restoration constrained by spatially variant point-spread functions},
  journal = {Journal of Seismic Exploration},
  year = {2026},
  volume = {0},
  number = {0},
  pages = {026260115},
  doi = {10.36922/jse026260115}
}
Kostenlos starten →