EUVIMEDEUVIMED entdecken
Crossref

A Diffusion Model Translator for Efficient Image-to-Image Translation

Mengfei Xia, Yu Zhou, Ran Yi, Yong-Jin Liu, Wenping Wang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 10272-10283

DOI: 10.1109/tpami.2024.3435448 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Mengfei Xia und 4 weiteren Autor:innen. Die Arbeit wurde bisher 59-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Natural Science Foundation, Shanghai Sailing Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Applying diffusion models to image-to-image translation (I2I) has recently received increasing attention due to its practical applications. Previous attempts inject information from the source image into each denoising step for an iterative refinement, thus resulting in a time-consuming implementation. We propose an efficient method that equips a diffusion model with a lightweight translator, dubbed a Diffusion Model Translator (DMT), to accomplish I2I. Specifically, we first offer theoretical justification that in employing the pioneering DDPM work for the I2I task, it is both feasible and sufficient to transfer the distribution from one domain to another only at some intermediate step. We further observe that the translation performance highly depends on the chosen timestep for domain transfer, and therefore propose a practical strategy to automatically select an appropriate timestep for a given task. We evaluate our approach on a range of I2I applications, including image stylization, image colorization, segmentation to image, and sketch to image, to validate its efficacy and general utility. The comparisons show that our DMT surpasses existing methods in both quality and efficiency. Code is available at https://github.com/THU-LYJ-Lab/dmt.

Förderung

  • National Natural Science Foundation of China
  • Beijing Natural Science Foundation
  • Shanghai Sailing Program
  • CAST

Zitieren

APA

Xia, M., Zhou, Y., Yi, R., Liu, Y. J., & Wang, W. (2024). A Diffusion Model Translator for Efficient Image-to-Image Translation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 10272-10283. https://doi.org/10.1109/tpami.2024.3435448

Vancouver

Xia M, Zhou Y, Yi R, Liu YJ, Wang W. A Diffusion Model Translator for Efficient Image-to-Image Translation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):10272-10283. doi:10.1109/tpami.2024.3435448

BibTeX
@article{Xia2024,
  author = {Xia, Mengfei and Zhou, Yu and Yi, Ran and Liu, Yong-Jin and Wang, Wenping},
  title = {A Diffusion Model Translator for Efficient Image-to-Image Translation},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {12},
  pages = {10272--10283},
  doi = {10.1109/tpami.2024.3435448}
}
Kostenlos starten →