EUVIMEDEUVIMED entdecken
Crossref

From Missing Pieces to Masterpieces: Image Completion With Context-Adaptive Diffusion

Pourya Shamsolmoali, Masoumeh Zareapoor, Huiyu Zhou, Michael Felsberg, Dacheng Tao, Xuelong Li

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-07 · 47 (7) · 6073-6087

DOI: 10.1109/tpami.2025.3558092 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-07. Verfasst von Pourya Shamsolmoali und 5 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 73 Literaturangaben. Gefördert von: University of York Research, National Research Foundation Singapore, Vetenskapsrådet.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Image completion is a challenging task, particularly when ensuring that generated content seamlessly integrates with existing parts of an image. While recent diffusion models have shown promise, they often struggle with maintaining coherence between known and unknown (missing) regions. This issue arises from the lack of explicit spatial and semantic alignment during the diffusion process, resulting in content that does not smoothly integrate with the original image. Additionally, diffusion models typically rely on global learned distributions rather than localized features, leading to inconsistencies between the generated and existing image parts. In this work, we propose ConFill, a novel framework that introduces a Context-Adaptive Discrepancy (CAD) model to ensure that intermediate distributions of known and unknown regions are closely aligned throughout the diffusion process. By incorporating CAD, our model progressively reduces discrepancies between generated and original images at each diffusion step, leading to contextually aligned completion. Moreover, ConFill uses a new Dynamic Sampling mechanism that adaptively increases the sampling rate in regions with high reconstruction complexity. This approach enables precise adjustments, enhancing detail and integration in restored areas. Extensive experiments demonstrate that ConFill outperforms current methods, setting a new benchmark in image completion.

Förderung

  • University of York Research
  • National Research Foundation Singapore
  • Vetenskapsrådet

Zitieren

APA

Shamsolmoali, P., Zareapoor, M., Zhou, H., Felsberg, M., Tao, D., & Li, X. (2025). From Missing Pieces to Masterpieces: Image Completion With Context-Adaptive Diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(7), 6073-6087. https://doi.org/10.1109/tpami.2025.3558092

Vancouver

Shamsolmoali P, Zareapoor M, Zhou H, Felsberg M, Tao D, Li X. From Missing Pieces to Masterpieces: Image Completion With Context-Adaptive Diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(7):6073-6087. doi:10.1109/tpami.2025.3558092

BibTeX
@article{Shamsolmoali2025,
  author = {Shamsolmoali, Pourya and Zareapoor, Masoumeh and Zhou, Huiyu and Felsberg, Michael and Tao, Dacheng and Li, Xuelong},
  title = {From Missing Pieces to Masterpieces: Image Completion With Context-Adaptive Diffusion},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {7},
  pages = {6073--6087},
  doi = {10.1109/tpami.2025.3558092}
}
Kostenlos starten →