DeepRFTv2: Kernel-level Learning for Image Deblurring

• URL: http://arxiv.org/abs/2511.21132v1
• Date: Wed, 26 Nov 2025 07:30:41 GMT
• Title: DeepRFTv2: Kernel-level Learning for Image Deblurring
• Authors: Xintian Mao, Haofei Song, Yin-Nian Liu, Qingli Li, Yan Wang,
• Abstract summary: It is well-known that if a network aims to learn how to deblur, it should understand the blur process.<n>We propose Fourier Kernel Estimator (FKE) to enable the deblur model to understand the essence of the blur.<n>Our method achieves state-of-the-art motion deblurring results and show potential for handling other kernel-related problems.
• Score: 21.144472443267
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: It is well-known that if a network aims to learn how to deblur, it should understand the blur process. Blurring is naturally caused by the convolution of the sharp image with the blur kernel. Thus, allowing the network to learn the blur process in the kernel-level can significantly improve the image deblurring performance. But, current deep networks are still at the pixel-level learning stage, either performing end-to-end pixel-level restoration or stage-wise pseudo kernel-level restoration, failing to enable the deblur model to understand the essence of the blur. To this end, we propose Fourier Kernel Estimator (FKE), which considers the activation operation in Fourier space and converts the convolution problem in the spatial domain to a multiplication problem in Fourier space. Our FKE, jointly optimized with the deblur model, enables the network to learn the kernel-level blur process with low complexity and without any additional supervision. Furthermore, we change the convolution object of the kernel from ``image" to network extracted ``feature", whose rich semantic and structural information is more suitable to blur process learning. With the convolution of the feature and the estimated kernel, our model can learn the essence of blur in kernel-level. To further improve the efficiency of feature extraction, we design a decoupled multi-scale architecture with multiple hierarchical sub-unets with a reversible strategy, which allows better multi-scale encoding and decoding in low training memory. Extensive experiments indicate that our method achieves state-of-the-art motion deblurring results and show potential for handling other kernel-related problems. Analysis also shows our kernel estimator is able to learn physically meaningful kernels. The code will be available at https://github.com/DeepMed-Lab-ECNU/Single-Image-Deblur.

Related papers

• LeRF: Learning Resampling Function for Adaptive and Efficient Image Interpolation [64.34935748707673]
  Recent deep neural networks (DNNs) have made impressive progress in performance by introducing learned data priors. We propose a novel method of Learning Resampling (termed LeRF) which takes advantage of both the structural priors learned by DNNs and the locally continuous assumption. LeRF assigns spatially varying resampling functions to input image pixels and learns to predict the shapes of these resampling functions with a neural network.
  arXiv  Detail & Related papers  (2024-07-13T16:09:45Z)
• NSD-DIL: Null-Shot Deblurring Using Deep Identity Learning [0.02932486408310998]
  We introduce Deep Identity Learning (DIL), a novel learning strategy that includes a dedicated regularization term based on the properties of linear systems. Since it is purely image-data-independent, we term our model as Null-Shot deblurring Using Deep Identity Learning (NSD-DIL) Our experiments show that the proposed method outperforms both traditional and deep learning based deblurring methods.
  arXiv  Detail & Related papers  (2024-07-05T18:56:31Z)
• Blind Image Deblurring with FFT-ReLU Sparsity Prior [1.179778723980276]
  Blind image deblurring is the process of recovering a sharp image from a blurred one without prior knowledge about the blur kernel. We introduce a method that leverages a prior which targets the blur kernel to achieve effective deblurring across a wide range of image types.
  arXiv  Detail & Related papers  (2024-06-12T15:51:39Z)
• Deep Multi-Threshold Spiking-UNet for Image Processing [51.88730892920031]
  This paper introduces the novel concept of Spiking-UNet for image processing, which combines the power of Spiking Neural Networks (SNNs) with the U-Net architecture. To achieve an efficient Spiking-UNet, we face two primary challenges: ensuring high-fidelity information propagation through the network via spikes and formulating an effective training strategy. Experimental results show that, on image segmentation and denoising, our Spiking-UNet achieves comparable performance to its non-spiking counterpart.
  arXiv  Detail & Related papers  (2023-07-20T16:00:19Z)
• Rank-Enhanced Low-Dimensional Convolution Set for Hyperspectral Image Denoising [50.039949798156826]
  This paper tackles the challenging problem of hyperspectral (HS) image denoising. We propose rank-enhanced low-dimensional convolution set (Re-ConvSet) We then incorporate Re-ConvSet into the widely-used U-Net architecture to construct an HS image denoising method.
  arXiv  Detail & Related papers  (2022-07-09T13:35:12Z)
• Learning with convolution and pooling operations in kernel methods [8.528384027684192]
  Recent empirical work has shown that hierarchical convolutional kernels improve the performance of kernel methods in image classification tasks. We study the precise interplay between approximation and generalization in convolutional architectures. Our results quantify how choosing an architecture adapted to the target function leads to a large improvement in the sample complexity.
  arXiv  Detail & Related papers  (2021-11-16T09:00:44Z)
• Content-Aware Convolutional Neural Networks [98.97634685964819]
  Convolutional Neural Networks (CNNs) have achieved great success due to the powerful feature learning ability of convolution layers. We propose a Content-aware Convolution (CAC) that automatically detects the smooth windows and applies a 1x1 convolutional kernel to replace the original large kernel.
  arXiv  Detail & Related papers  (2021-06-30T03:54:35Z)
• Explore Image Deblurring via Blur Kernel Space [17.67255729783263]
  We propose an alternating optimization algorithm for blind image deblurring. It approximates an unseen blur operator by a kernel in the encoded space and searches for the corresponding sharp image. Our method can be used for blur synthesis by transferring existing blur operators from a given dataset into a new domain.
  arXiv  Detail & Related papers  (2021-04-01T07:52:53Z)
• Blur Invariant Kernel-Adaptive Network for Single Image Blind deblurring [0.886014926770622]
  We present a novel, blind, single image deblurring method that utilizes information regarding blur kernels. We first introduce a kernel estimation network that produces adaptive blur kernels based on the analysis of the blurred image. We propose a deblurring network that restores sharp images using the estimated blur kernel.
  arXiv  Detail & Related papers  (2020-07-09T03:53:33Z)
• Neural Sparse Representation for Image Restoration [116.72107034624344]
  Inspired by the robustness and efficiency of sparse coding based image restoration models, we investigate the sparsity of neurons in deep networks. Our method structurally enforces sparsity constraints upon hidden neurons. Experiments show that sparse representation is crucial in deep neural networks for multiple image restoration tasks.
  arXiv  Detail & Related papers  (2020-06-08T05:15:17Z)
• Deblurring using Analysis-Synthesis Networks Pair [6.09170287691728]
  Blind image deblurring remains a challenging problem for modern artificial neural networks. We propose a new architecture which breaks the deblurring network into an analysis network which estimates the blur, and a synthesis network that uses this kernel to deblur the image.
  arXiv  Detail & Related papers  (2020-04-06T19:32:51Z)
• Deep Blind Video Super-resolution [85.79696784460887]
  We propose a deep convolutional neural network (CNN) model to solve video SR by a blur kernel modeling approach. The proposed CNN model consists of motion blur estimation, motion estimation, and latent image restoration modules. We show that the proposed algorithm is able to generate clearer images with finer structural details.
  arXiv  Detail & Related papers  (2020-03-10T13:43:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.