mlsanityData to 14 Oct 2026

NFResNet: Multi-scale and U-shaped Networks for Deblurring

arXiv 2212.05909 ↗First posted 12 Dec 2022cs.CV eess.IVcited by 1

Not on the map. Why?

Abstract (arXiv)

Multi-Scale and U-shaped Networks are widely used in various image restoration problems, including deblurring. Keeping in mind the wide range of applications, we present a comparison of these architectures and their effects on image deblurring. We also introduce a new block called as NFResblock. It consists of a Fast Fourier Transformation layer and a series of modified Non-Linear Activation Free Blocks. Based on these architectures and additions, we introduce NFResnet and NFResnet+, which are modified multi-scale and U-Net architectures, respectively. We also use three different loss functions to train these architectures: Charbonnier Loss, Edge Loss, and Frequency Reconstruction Loss. Extensive experiments on the Deep Video Deblurring dataset, along with ablation studies for each component, have been presented in this paper. The proposed architectures achieve a considerable increase in Peak Signal to Noise (PSNR) ratio and Structural Similarity Index (SSIM) value.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 12 of its 20 references that are in the map. First posted on arXiv 12 Dec 2022.

Builds on

12 of 20 references.

References · 12

  1. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  2. 2016Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurringcited by 727
  3. 2022Simple Baselines for Image Restorationcited by 708
  4. 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 367
  5. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 362
  6. 2018Scale-recurrent Network for Deep Image Deblurringcited by 333
  7. 2021Rethinking Coarse-to-Fine Approach in Single Image Deblurringcited by 326
  8. 2019High Frequency Component Helps Explain the Generalization of Convolutional Neural Networkscited by 310
  9. 2019Deep Stacked Hierarchical Multi-patch Network for Image Deblurringcited by 206
  10. 2015Learning a Convolutional Neural Network for Non-uniform Motion Blur Removalcited by 149
  11. 2016From Motion Blur to Motion Flow: a Deep Learning Solution for Removing Heterogeneous Motion Blurcited by 81
  12. 2014Learning to Deblurcited by 66

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Intervening in Black Box: Concept Bottleneck Model for Enhancing Human Neural Network Mutual Understandingcited by 0