# Intriguing Findings of Frequency Selection for Image Deblurring

arXiv: https://arxiv.org/abs/2111.11745 · HTML: https://mlsanity.com/paper/2111.11745/

## Key facts

- Cited by 81 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 55 references that are in the map.
- First posted on arXiv 23 Nov 2021.

## Builds on (most cited first, 30 of 36)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Do Vision Transformers See Like Convolutional Neural Networks?](https://mlsanity.com/paper/2108.08810/) (2021)
- [FDA: Fourier Domain Adaptation for Semantic Segmentation](https://mlsanity.com/paper/2004.05498/) (2020)
- [DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks](https://mlsanity.com/paper/1711.07064/) (2017)
- [DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better](https://mlsanity.com/paper/1908.03826/) (2019)
- [Understanding Neural Networks Through Deep Visualization](https://mlsanity.com/paper/1506.06579/) (2015)
- [Scale-recurrent Network for Deep Image Deblurring](https://mlsanity.com/paper/1802.01770/) (2018)
- [Rethinking Coarse-to-Fine Approach in Single Image Deblurring](https://mlsanity.com/paper/2108.05054/) (2021)
- [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020)
- [Multi-Scale Progressive Fusion Network for Single Image Deraining](https://mlsanity.com/paper/2003.10985/) (2020)
- [Global Filter Networks for Image Classification](https://mlsanity.com/paper/2107.00645/) (2021)
- [HINet: Half Instance Normalization Network for Image Restoration](https://mlsanity.com/paper/2105.06086/) (2021)
- [Deep Stacked Hierarchical Multi-patch Network for Image Deblurring](https://mlsanity.com/paper/1904.03468/) (2019)
- [Deblurring by Realistic Blurring](https://mlsanity.com/paper/2004.01860/) (2020)
- [Human-Aware Motion Deblurring](https://mlsanity.com/paper/2001.06816/) (2020)
- [Learning a Convolutional Neural Network for Non-uniform Motion Blur Removal](https://mlsanity.com/paper/1503.00593/) (2015)
- [Spatially-Attentive Patch-Hierarchical Network for Adaptive Motion Deblurring](https://mlsanity.com/paper/2004.05343/) (2020)
- [Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training](https://mlsanity.com/paper/1911.07410/) (2019)
- [Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolution](https://mlsanity.com/paper/2003.07018/) (2020)
- [Spectral Representations for Convolutional Neural Networks](https://mlsanity.com/paper/1506.03767/) (2015)

## Built on by (most cited first, 30 of 81)

- [AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation](https://mlsanity.com/paper/2403.14614/) (2024)
- [FreqMamba: Viewing Mamba from a Frequency Perspective for Image Deraining](https://mlsanity.com/paper/2404.09476/) (2024)
- [Bidirectional Multi-Scale Implicit Neural Representations for Image Deraining](https://mlsanity.com/paper/2404.01547/) (2024)
- [FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining](https://mlsanity.com/paper/2405.19450/) (2024)
- [SGNet: Structure Guided Network via Gradient-Frequency Awareness for Depth Map Super-Resolution](https://mlsanity.com/paper/2312.05799/) (2023)
- [AdaRevD: Adaptive Patch Exiting Reversible Decoder Pushes the Limit of Image Deblurring](https://mlsanity.com/paper/2406.09135/) (2024)
- [From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspective](https://mlsanity.com/paper/2503.13165/) (2025)
- [I-MedSAM: Implicit Medical Image Segmentation with Segment Anything](https://mlsanity.com/paper/2311.17081/) (2023)
- [Towards Real-world Event-guided Low-light Video Enhancement and Deblurring](https://mlsanity.com/paper/2408.14916/) (2024)
- [Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring](https://mlsanity.com/paper/2404.13153/) (2024)
- [LoFormer: Local Frequency Transformer for Image Deblurring](https://mlsanity.com/paper/2407.16993/) (2024)
- [Dropout the High-rate Downsampling: A Novel Design Paradigm for UHD Image Restoration](https://mlsanity.com/paper/2411.06456/) (2024)
- [Truly Scale-Equivariant Deep Nets with Fourier Layers](https://mlsanity.com/paper/2311.02922/) (2023)
- [Video Quality Assessment: A Comprehensive Survey](https://mlsanity.com/paper/2412.04508/) (2024)
- [Causality-inspired Discriminative Feature Learning in Triple Domains for Gait Recognition](https://mlsanity.com/paper/2407.12519/) (2024)
- [NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results](https://mlsanity.com/paper/2505.12089/) (2025)
- [LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network](https://mlsanity.com/paper/2307.09815/) (2023)
- [SAM-Deblur: Let Segment Anything Boost Image Deblurring](https://mlsanity.com/paper/2309.02270/) (2023)
- [Annular Computational Imaging: Capture Clear Panoramic Images through Simple Lens](https://mlsanity.com/paper/2206.06070/) (2022)
- [NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolution](https://mlsanity.com/paper/2506.02197/) (2025)
- [Quad-Net: Quad-domain Network for CT Metal Artifact Reduction](https://mlsanity.com/paper/2207.11678/) (2022)
- [Spatial-frequency Dual-Domain Feature Fusion Network for Low-Light Remote Sensing Image Enhancement](https://mlsanity.com/paper/2404.17400/) (2024)
- [Image Deraining with Frequency-Enhanced State Space Model](https://mlsanity.com/paper/2405.16470/) (2024)
- [Lightweight Medical Image Restoration via Integrating Reliable Lesion-Semantic Driven Prior](https://mlsanity.com/paper/2504.11286/) (2025)
- [From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmark](https://mlsanity.com/paper/2604.15654/) (2026)
- [Real-World Efficient Blind Motion Deblurring via Blur Pixel Discretization](https://mlsanity.com/paper/2404.12168/) (2024)
- [CRNet: A Detail-Preserving Network for Unified Image Restoration and Enhancement Task](https://mlsanity.com/paper/2404.14132/) (2024)
- [Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restoration](https://mlsanity.com/paper/2406.07435/) (2024)
- [A Hybrid Transformer-Mamba Network for Single Image Deraining](https://mlsanity.com/paper/2409.00410/) (2024)
- [Exploring Temporal Dynamics in Event-based Eye Tracker](https://mlsanity.com/paper/2503.23725/) (2025)

## Abstract (arXiv)

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.