Fengze Liu

Fengze Liu

Auto-generated profile, based on publicly available information

Fengze Liu

The Johns Hopkins University

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 June 2023 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
XMXintian Mao
Xintian Mao
YLYiming Liu
Yiming Liu
FLFengze Liu
Fengze Liu
Qingli LiQingli Li
Qingli Li
WSWei Shen
Wei Shen
Yan WangYan Wang
Yan Wang
Blur was naturally analyzed in the frequency domain, by estimating the latent sharp image and the blur kernel given a blurry image. Recent progress on image deblurring always designs end-to-end architectures and aims at learning the difference between blurry and sharp image pairs from pixel-level, which inevitably overlooks the importance of blur kernels. This paper reveals an intriguing phenomenon that simply applying ReLU operation on the frequency domain of a blur image followed by inverse Fourier transform, i.e., frequency selection, provides faithful information about the blur pattern (e.g., the blur direction and blur level, implicitly shows the kernel pattern). Based on this observation, we attempt to leverage kernel-level information for image deblurring networks by inserting Fourier transform, ReLU operation, and inverse Fourier transform to the standard ResBlock. 1 × 1 convolution is further added to let the network modulate flexible thresholds for frequency selection. We term our newly built block as Res FFT-ReLU Block, which takes advantages of both kernel-level and pixel-level features via learning frequency-spatial dual-domain representations. Extensive experiments are conducted to acquire a thorough analysis on the insights of the method. Moreover, after plugging the proposed block into NAFNet, we can achieve 33.85 dB in PSNR on GoPro dataset. Our method noticeably improves backbone architectures without introducing many parameters, while maintaining low computational complexity. Code is available at https://github.com/DeepMed-Lab/DeepRFT-AAAI2023.

10 October 2019
Verified
Book Chapter
Closed access
PDF file
FLFengze Liu
Fengze Liu
LXLingxi Xie
Lingxi Xie
YXYingda Xia
Yingda Xia
EFElliot Fishman
Elliot Fishman
AYAlan Yuille
Alan Yuille

29 November 2022 in arXiv
Verified
Preprint
Open access
PDF file
XMXintian Mao
Xintian Mao
YLYiming Liu
Yiming Liu
FLFengze Liu
Fengze Liu
Qingli LiQingli Li
Qingli Li
WSWei Shen
Wei Shen
Yan WangYan Wang
Yan Wang
Blur was naturally analyzed in the frequency domain, by estimating the latent sharp image and the blur kernel given a blurry image. Recent progress on image deblurring always designs end-to-end architectures and aims at learning the difference between blurry and sharp image pairs from pixel-level, which inevitably overlooks the importance of blur kernels. This paper reveals an intriguing phenomenon that simply applying ReLU operation on the frequency domain of a blur image followed by inverse Fourier transform, i.e., frequency selection, provides faithful information about the blur pattern (e.g., the blur direction and blur level, implicitly shows the kernel pattern). Based on this observation, we attempt to leverage kernel-level information for image deblurring networks by inserting Fourier transform, ReLU operation, and inverse Fourier transform to the standard ResBlock. 1x1 convolution is further added to let the network modulate flexible thresholds for frequency selection. We term our newly built block as Res FFT-ReLU Block, which takes advantages of both kernel-level and pixel-level features via learning frequency-spatial dual-domain representations. Extensive experiments are conducted to acquire a thorough analysis on the insights of the method. Moreover, after plugging the proposed block into NAFNet, we can achieve 33.85 dB in PSNR on GoPro dataset. Our method noticeably improves backbone architectures without introducing many parameters, while maintaining low computational complexity. Code is available at https://github.com/DeepMed-Lab/DeepRFT-AAAI2023.

10 October 2019
Verified
Book Chapter
Closed access
PDF file
FLFengze Liu
Fengze Liu
YZYuyin Zhou
Yuyin Zhou
EFElliot Fishman
Elliot Fishman
AYAlan Yuille
Alan Yuille