TY - GEN
T1 - Deep Learning for Face Deblurring
T2 - 12th IEEE International Conference on Cyber Security and Cloud Computing, CSCloud 2025
AU - Wu, Heye
AU - Yu, Jing
AU - Wang, Kexin
AU - Wei, Yihang
AU - Niu, Qianhang
AU - Cong, Yijun
AU - Gai, Keke
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - 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.
AB - 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.
KW - diffusion model
KW - Face image deblurring
KW - generative adversarial network
KW - variational autoencoder
UR - https://www.scopus.com/pages/publications/105030335177
U2 - 10.1109/CSCloud66326.2025.00039
DO - 10.1109/CSCloud66326.2025.00039
M3 - Conference contribution
AN - SCOPUS:105030335177
T3 - Proceedings - 2025 IEEE 12th International Conference on Cyber Security and Cloud Computing, CSCloud 2025
SP - 202
EP - 207
BT - Proceedings - 2025 IEEE 12th International Conference on Cyber Security and Cloud Computing, CSCloud 2025
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 7 November 2025 through 9 November 2025
ER -