Skip to main content

2024 | OriginalPaper | Buchkapitel

Face Super-Resolution Model Based on Diffusion Model

verfasst von : Tianyi Feng, Yongping Xie

Erschienen in: Communications, Signal Processing, and Systems

Verlag: Springer Nature Singapore

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

The problem of restoring high-resolution images from blurry images has long been a concern, and traditional methods of directly interpolating low-resolution images to obtain high-resolution images are simple but ineffective. Inspired by SR3, we propose a super-resolution model of human faces based on the diffusion model, which achieves super-resolution through a random iterative denoising process. In this paper, we have used a residual block that integrates multi-scale spatial attention and coordinate attention. Additionally, we have enhanced the restoration of image details through a global attention model. These advancements effectively address the discrepancy between automated evaluation metrics and human perception in high-frequency details for super-resolution models. Through evaluation of the standard eight-fold super-resolution task on CelebA-HQ, our model performs well and achieves competitive scores on SSIM and PSNR metrics.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
2.
Zurück zum Zitat Kingma DP, Dhariwal P (2018) Glow: generative flow with invertible \(1\times 1\) convolutions. In: Advances in neural information processing systems, vol 31 Kingma DP, Dhariwal P (2018) Glow: generative flow with invertible \(1\times 1\) convolutions. In: Advances in neural information processing systems, vol 31
3.
Zurück zum Zitat Karras T, Aila T, Laine S, Lehtinen J (2017) Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 Karras T, Aila T, Laine S, Lehtinen J (2017) Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:​1710.​10196
4.
Zurück zum Zitat Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V, Courville AC (2017) Improved training of wasserstein GANs. In: Advances in neural information processing systems, vol 30 Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V, Courville AC (2017) Improved training of wasserstein GANs. In: Advances in neural information processing systems, vol 30
5.
Zurück zum Zitat Ravuri S, Vinyals O (2019) Classification accuracy score for conditional generative models. In: Advances in neural information processing systems, vol 32 Ravuri S, Vinyals O (2019) Classification accuracy score for conditional generative models. In: Advances in neural information processing systems, vol 32
6.
Zurück zum Zitat Lim B, Son S, Kim H, Nah S, Lee KM (2017) Enhanced deep residual networks for single image super-resolution. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 136–144 Lim B, Son S, Kim H, Nah S, Lee KM (2017) Enhanced deep residual networks for single image super-resolution. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 136–144
7.
Zurück zum Zitat Wang X, Yu K, Wu S, Gu J, Liu Y, Dong C, Qiao Y, Loy CC (2018) ESRGAN: enhanced super-resolution generative adversarial networks. In: Proceedings of the European conference on computer vision (ECCV) workshops, p 0 Wang X, Yu K, Wu S, Gu J, Liu Y, Dong C, Qiao Y, Loy CC (2018) ESRGAN: enhanced super-resolution generative adversarial networks. In: Proceedings of the European conference on computer vision (ECCV) workshops, p 0
8.
Zurück zum Zitat Liang J, Cao J, Sun G, Zhang K, Van Gool L, Timofte R (2021) SwinIR: image restoration using Swin transformer. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 1833–1844 Liang J, Cao J, Sun G, Zhang K, Van Gool L, Timofte R (2021) SwinIR: image restoration using Swin transformer. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 1833–1844
9.
Zurück zum Zitat Chen Y, Tai Y, Liu X, Shen C, Yang J (2018) FSRNet: end-to-end learning face super-resolution with facial priors. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2492–2501 Chen Y, Tai Y, Liu X, Shen C, Yang J (2018) FSRNet: end-to-end learning face super-resolution with facial priors. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2492–2501
10.
Zurück zum Zitat Menon S, Damian A, Hu S, Ravi N, Rudin C (2020) Pulse: self-supervised photo upsampling via latent space exploration of generative models. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 2437–2445 Menon S, Damian A, Hu S, Ravi N, Rudin C (2020) Pulse: self-supervised photo upsampling via latent space exploration of generative models. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 2437–2445
11.
Zurück zum Zitat Rombach R, Blattmann A, Lorenz D, Esser P, Ommer B (2022) High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 10684–10695 Rombach R, Blattmann A, Lorenz D, Esser P, Ommer B (2022) High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 10684–10695
12.
Zurück zum Zitat Ho J, Saharia C, Chan W, Fleet DJ, Norouzi M, Salimans T (2022) Cascaded diffusion models for high fidelity image generation. J Mach Learn Res 23(47):1–33MathSciNet Ho J, Saharia C, Chan W, Fleet DJ, Norouzi M, Salimans T (2022) Cascaded diffusion models for high fidelity image generation. J Mach Learn Res 23(47):1–33MathSciNet
13.
Zurück zum Zitat Saharia C, Ho J, Chan W, Salimans T, Fleet DJ, Norouzi M (2022) Image super-resolution via iterative refinement. IEEE Trans Pattern Anal Mach Intell Saharia C, Ho J, Chan W, Salimans T, Fleet DJ, Norouzi M (2022) Image super-resolution via iterative refinement. IEEE Trans Pattern Anal Mach Intell
14.
Zurück zum Zitat Su J-N, Gan M, Chen G-Y, Yin J-L, Chen CP (2022) Global learnable attention for single image super-resolution. IEEE Trans Pattern Anal Mach Intell Su J-N, Gan M, Chen G-Y, Yin J-L, Chen CP (2022) Global learnable attention for single image super-resolution. IEEE Trans Pattern Anal Mach Intell
15.
Zurück zum Zitat Gao S, Liu X, Zeng B, Xu S, Li Y, Luo X, Liu J, Zhen X, Zhang B (2023) Implicit diffusion models for continuous super-resolution. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 10021–10030 Gao S, Liu X, Zeng B, Xu S, Li Y, Luo X, Liu J, Zhen X, Zhang B (2023) Implicit diffusion models for continuous super-resolution. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 10021–10030
Metadaten
Titel
Face Super-Resolution Model Based on Diffusion Model
verfasst von
Tianyi Feng
Yongping Xie
Copyright-Jahr
2024
Verlag
Springer Nature Singapore
DOI
https://doi.org/10.1007/978-981-99-7502-0_6

Neuer Inhalt