Deep Learning for Face Deblurring: A Survey

  • Heye Wu
  • , Jing Yu*
  • , Kexin Wang
  • , Yihang Wei*
  • , Qianhang Niu
  • , Yijun Cong
  • , Keke Gai
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Face image deblurring has been widely used in various fields. However, existing deblurring methods still face challenges such as low robustness and low precision. This work summarizes these challenges by investigating and analyzing the current state of face image deblurring methods. This survey explores three key aspects: adversarial-network-based generative approaches, auto-encoder-based variational approaches, and diffusion-model-based approaches, with an emphasis on the diffusion-model-based ones. Moreover, this work evaluates experimental results over widely-compared metrics to analyze the performance of the current diffusion models systematically. The findings of this survey provide reference and future research directions for face image deblurring.

Original languageEnglish
Title of host publicationProceedings - 2025 IEEE 12th International Conference on Cyber Security and Cloud Computing, CSCloud 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages202-207
Number of pages6
ISBN (Electronic)9798331587819
DOIs
Publication statusPublished - 2025
Event12th IEEE International Conference on Cyber Security and Cloud Computing, CSCloud 2025 - New York City, United States
Duration: 7 Nov 20259 Nov 2025

Publication series

NameProceedings - 2025 IEEE 12th International Conference on Cyber Security and Cloud Computing, CSCloud 2025

Conference

Conference12th IEEE International Conference on Cyber Security and Cloud Computing, CSCloud 2025
Country/TerritoryUnited States
CityNew York City
Period7/11/259/11/25

Keywords

  • diffusion model
  • Face image deblurring
  • generative adversarial network
  • variational autoencoder

Fingerprint

Dive into the research topics of 'Deep Learning for Face Deblurring: A Survey'. Together they form a unique fingerprint.

Cite this