Learning Deblurring Texture Prior from Unpaired Data with Diffusion Model

• URL: http://arxiv.org/abs/2507.13599v1
• Date: Fri, 18 Jul 2025 01:50:31 GMT
• Title: Learning Deblurring Texture Prior from Unpaired Data with Diffusion Model
• Authors: Chengxu Liu, Lu Qi, Jinshan Pan, Xueming Qian, Ming-Hsuan Yang,
• Abstract summary: We propose a novel diffusion model (DM)-based framework, dubbed ours, for image deblurring.<n>ours performs DM to generate the prior knowledge that aids in recovering the textures of blurry images.<n>To fully exploit the generated texture priors, we present the Texture Transfer Transformer layer (TTformer)
• Score: 92.61216319417208
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Since acquiring large amounts of realistic blurry-sharp image pairs is difficult and expensive, learning blind image deblurring from unpaired data is a more practical and promising solution. Unfortunately, dominant approaches rely heavily on adversarial learning to bridge the gap from blurry domains to sharp domains, ignoring the complex and unpredictable nature of real-world blur patterns. In this paper, we propose a novel diffusion model (DM)-based framework, dubbed \ours, for image deblurring by learning spatially varying texture prior from unpaired data. In particular, \ours performs DM to generate the prior knowledge that aids in recovering the textures of blurry images. To implement this, we propose a Texture Prior Encoder (TPE) that introduces a memory mechanism to represent the image textures and provides supervision for DM training. To fully exploit the generated texture priors, we present the Texture Transfer Transformer layer (TTformer), in which a novel Filter-Modulated Multi-head Self-Attention (FM-MSA) efficiently removes spatially varying blurring through adaptive filtering. Furthermore, we implement a wavelet-based adversarial loss to preserve high-frequency texture details. Extensive evaluations show that \ours provides a promising unsupervised deblurring solution and outperforms SOTA methods in widely-used benchmarks.

Related papers

• Self-Supervised Enhancement of Forward-Looking Sonar Images: Bridging Cross-Modal Degradation Gaps through Feature Space Transformation and Multi-Frame Fusion [17.384482405769567]
  Enhancing forward-looking sonar images is critical for accurate underwater target detection.<n>We propose a feature-space transformation that maps sonar images from the pixel domain to a robust feature domain.<n>Our method significantly outperforms existing approaches, effectively suppressing noise, preserving detailed edges, and substantially improving brightness.
  arXiv  Detail & Related papers  (2025-04-15T08:34:56Z)
• 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)
• Robust CLIP-Based Detector for Exposing Diffusion Model-Generated Images [13.089550724738436]
  Diffusion models (DMs) have revolutionized image generation, producing high-quality images with applications spanning various fields. Their ability to create hyper-realistic images poses significant challenges in distinguishing between real and synthetic content. This work introduces a robust detection framework that integrates image and text features extracted by CLIP model with a Multilayer Perceptron (MLP) classifier.
  arXiv  Detail & Related papers  (2024-04-19T14:30:41Z)
• A Multi-scale Generalized Shrinkage Threshold Network for Image Blind Deblurring in Remote Sensing [5.957520165711732]
  We propose a new blind deblurring learning framework that utilizes alternating iterations of shrinkage thresholds. We also propose a deep proximal mapping module in the image domain, which combines a generalized shrinkage threshold with a multi-scale prior feature extraction block.
  arXiv  Detail & Related papers  (2023-09-14T08:48:44Z)
• Person Image Synthesis via Denoising Diffusion Model [116.34633988927429]
  We show how denoising diffusion models can be applied for high-fidelity person image synthesis. Our results on two large-scale benchmarks and a user study demonstrate the photorealism of our proposed approach under challenging scenarios.
  arXiv  Detail & Related papers  (2022-11-22T18:59:50Z)
• Learning Degradation Representations for Image Deblurring [37.80709422920307]
  We propose a framework to learn spatially adaptive degradation representations of blurry images. A novel joint image reblurring and deblurring learning process is presented to improve the expressiveness of degradation representations. Experiments on the GoPro and RealBlur datasets demonstrate that our proposed deblurring framework with the learned degradation representations outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-08-10T09:53:16Z)
• Controllable Person Image Synthesis with Spatially-Adaptive Warped Normalization [72.65828901909708]
  Controllable person image generation aims to produce realistic human images with desirable attributes. We introduce a novel Spatially-Adaptive Warped Normalization (SAWN), which integrates a learned flow-field to warp modulation parameters. We propose a novel self-training part replacement strategy to refine the pretrained model for the texture-transfer task.
  arXiv  Detail & Related papers  (2021-05-31T07:07:44Z)
• Towards Enhancing Fine-grained Details for Image Matting [40.17208660790402]
  We argue that recovering microscopic details relies on low-level but high-definition texture features. Our model consists of a conventional encoder-decoder Semantic Path and an independent down-sampling-free Textural Compensate Path. Our method outperforms previous start-of-the-art methods on the Composition-1k dataset.
  arXiv  Detail & Related papers  (2021-01-22T13:20:23Z)
• Self-Adaptively Learning to Demoire from Focused and Defocused Image Pairs [97.67638106818613]
  Moire artifacts are common in digital photography, resulting from the interference between high-frequency scene content and the color filter array of the camera. Existing deep learning-based demoireing methods trained on large scale iteration are limited in handling various complex moire patterns. We propose a self-adaptive learning method for demoireing a high-frequency image, with the help of an additional defocused moire-free blur image.
  arXiv  Detail & Related papers  (2020-11-03T23:09:02Z)
• Image Fine-grained Inpainting [89.17316318927621]
  We present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields. To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss. We also employ a discriminator with local and global branches to ensure local-global contents consistency.
  arXiv  Detail & Related papers  (2020-02-07T03:45:25Z)

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.