EUVIMEDEUVIMED entdecken
Crossref

Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression

Zheng Chen, Mingde Zhou, Jinpei Guo, Jiale Yuan, Yifei Ji, Yulun Zhang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (5) · 3192-3200

DOI: 10.1609/aaai.v40i5.37313 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zheng Chen und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Diffusion-based image compression has demonstrated impressive perceptual performance. However, it suffers from two critical drawbacks: (1) excessive decoding latency due to multi-step sampling, and (2) poor fidelity resulting from over-reliance on generative priors. To address these issues, we propose SODEC, a novel single-step diffusion image compression model. We argue that in image compression, a sufficiently informative latent renders multi-step refinement unnecessary. Based on this insight, we leverage a pre-trained VAE-based model to produce latents with rich information, and replace the iterative denoising process with a single-step decoding. Meanwhile, to improve fidelity, we introduce the fidelity guidance module, encouraging output that is faithful to the original image. Furthermore, we design the rate annealing training strategy to enable effective training under extremely low bitrates. Extensive experiments show that SODEC significantly outperforms existing methods, achieving superior rate-distortion-perception performance. Moreover, compared to previous diffusion-based compression models, SODEC improves decoding speed by more than 20×.

Zitieren

APA

Chen, Z., Zhou, M., Guo, J., Yuan, J., Ji, Y., & Zhang, Y. (2026). Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression. Proceedings of the AAAI Conference on Artificial Intelligence, 40(5), 3192-3200. https://doi.org/10.1609/aaai.v40i5.37313

Vancouver

Chen Z, Zhou M, Guo J, Yuan J, Ji Y, Zhang Y. Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(5):3192-3200. doi:10.1609/aaai.v40i5.37313

BibTeX
@article{Chen2026,
  author = {Chen, Zheng and Zhou, Mingde and Guo, Jinpei and Yuan, Jiale and Ji, Yifei and Zhang, Yulun},
  title = {Steering One-Step Diffusion Model with Fidelity-Rich Decoder for Fast Image Compression},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {5},
  pages = {3192--3200},
  doi = {10.1609/aaai.v40i5.37313}
}
Kostenlos starten →