Towards Unified Image Deblurring using a Mixture-of-Experts Decoder

• URL: http://arxiv.org/abs/2508.06228v2
• Date: Tue, 07 Oct 2025 09:52:40 GMT
• Title: Towards Unified Image Deblurring using a Mixture-of-Experts Decoder
• Authors: Daniel Feijoo, Paula Garrido-Mellado, Jaesung Rim, Alvaro Garcia, Marcos V. Conde,
• Abstract summary: We introduce the first all-in-one deblurring method capable of efficiently restoring images affected by diverse blur degradations.<n>We propose a mixture-of-experts (MoE) decoding module, which dynamically routes image features based on the recognized blur degradation.<n>Our unified approach achieves performance comparable to dedicated task-specific models, but also shows promising generalization to unseen blur scenarios.
• Score: 14.477901039949339
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Image deblurring, removing blurring artifacts from images, is a fundamental task in computational photography and low-level computer vision. Existing approaches focus on specialized solutions tailored to particular blur types, thus, these solutions lack generalization. This limitation in current methods implies requiring multiple models to cover several blur types, which is not practical in many real scenarios. In this paper, we introduce the first all-in-one deblurring method capable of efficiently restoring images affected by diverse blur degradations, including global motion, local motion, blur in low-light conditions, and defocus blur. We propose a mixture-of-experts (MoE) decoding module, which dynamically routes image features based on the recognized blur degradation, enabling precise and efficient restoration in an end-to-end manner. Our unified approach not only achieves performance comparable to dedicated task-specific models, but also shows promising generalization to unseen blur scenarios, particularly when leveraging appropriate expert selection. Code available at https://github.com/cidautai/DeMoE.

Related papers

• Nonlocal Retinex-Based Variational Model and its Deep Unfolding Twin for Low-Light Image Enhancement [3.174882428337821]
  We propose a variational method for low-light image enhancement based on the Retinex decomposition.<n>A color correction pre-processing step is applied to the low-light image, which is then used as the observed input in the decomposition.<n>We extend the model by introducing its deep unfolding counterpart, in which the operators are replaced with learnable networks.
  arXiv  Detail & Related papers  (2025-04-10T14:48:26Z)
• DiffUHaul: A Training-Free Method for Object Dragging in Images [78.93531472479202]
  We propose a training-free method, dubbed DiffUHaul, for the object dragging task. We first apply attention masking in each denoising step to make the generation more disentangled across different objects. In the early denoising steps, we interpolate the attention features between source and target images to smoothly fuse new layouts with the original appearance.
  arXiv  Detail & Related papers  (2024-06-03T17:59:53Z)
• Exposure Bracketing Is All You Need For A High-Quality Image [50.822601495422916]
  Multi-exposure images are complementary in denoising, deblurring, high dynamic range imaging, and super-resolution.<n>We propose to utilize exposure bracketing photography to get a high-quality image by combining these tasks in this work.<n>In particular, a temporally modulated recurrent network (TMRNet) and self-supervised adaptation method are proposed.
  arXiv  Detail & Related papers  (2024-01-01T14:14:35Z)
• Take a Prior from Other Tasks for Severe Blur Removal [52.380201909782684]
  Cross-level feature learning strategy based on knowledge distillation to learn the priors. Semantic prior embedding layer with multi-level aggregation and semantic attention transformation to integrate the priors effectively. Experiments on natural image deblurring benchmarks and real-world images, such as GoPro and RealBlur datasets, demonstrate our method's effectiveness and ability.
  arXiv  Detail & Related papers  (2023-02-14T08:30:51Z)
• A Generalist Framework for Panoptic Segmentation of Images and Videos [61.61453194912186]
  We formulate panoptic segmentation as a discrete data generation problem, without relying on inductive bias of the task. A diffusion model is proposed to model panoptic masks, with a simple architecture and generic loss function. Our method is capable of modeling video (in a streaming setting) and thereby learns to track object instances automatically.
  arXiv  Detail & Related papers  (2022-10-12T16:18:25Z)
• MC-Blur: A Comprehensive Benchmark for Image Deblurring [127.6301230023318]
  In most real-world images, blur is caused by different factors, e.g., motion and defocus. We construct a new large-scale multi-cause image deblurring dataset (called MC-Blur) Based on the MC-Blur dataset, we conduct extensive benchmarking studies to compare SOTA methods in different scenarios.
  arXiv  Detail & Related papers  (2021-12-01T02:10:42Z)
• Single Image Non-uniform Blur Kernel Estimation via Adaptive Basis Decomposition [1.854931308524932]
  We propose a general, non-parametric model for dense non-uniform motion blur estimation. We show that our method overcomes the limitations of existing non-uniform motion blur estimation.
  arXiv  Detail & Related papers  (2021-02-01T18:02:31Z)
• Blur-Attention: A boosting mechanism for non-uniform blurred image restoration [27.075713246257596]
  We propose a blur-attention module to dynamically capture the spatially varying features of non-uniform blurred images. By introducing the blur-attention network into a conditional generation adversarial framework, we propose an end-to-end blind motion deblurring method. Experimental results show that the deblurring capability of our method achieved outstanding objective performance in terms of PSNR, SSIM, and subjective visual quality.
  arXiv  Detail & Related papers  (2020-08-19T16:07:06Z)
• Prior-enlightened and Motion-robust Video Deblurring [29.158836861982742]
  PRiOr-enlightened and MOTION-robust deblurring model (PROMOTION) suitable for challenging blurs. We use 3D group convolution to efficiently encode heterogeneous prior information. We also design the priors representing blur distribution, to better handle non-uniform blur-temporal domain.
  arXiv  Detail & Related papers  (2020-03-25T04:16:56Z)
• PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models [77.32079593577821]
  PULSE (Photo Upsampling via Latent Space Exploration) generates high-resolution, realistic images at resolutions previously unseen in the literature. Our method outperforms state-of-the-art methods in perceptual quality at higher resolutions and scale factors than previously possible.
  arXiv  Detail & Related papers  (2020-03-08T16:44:31Z)

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.