Generative Latent Kernel Modeling for Blind Motion Deblurring

• URL: http://arxiv.org/abs/2507.09285v1
• Date: Sat, 12 Jul 2025 13:48:10 GMT
• Title: Generative Latent Kernel Modeling for Blind Motion Deblurring
• Authors: Chenhao Ding, Jiangtao Zhang, Zongsheng Yue, Hui Wang, Qian Zhao, Deyu Meng,
• Abstract summary: We present a novel framework for kernel blur estimation based on a deep generative network generator.<n>We achieve state-of-the-art performance on challenging benchmark datasets.
• Score: 43.79789971884913
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep prior-based approaches have demonstrated remarkable success in blind motion deblurring (BMD) recently. These methods, however, are often limited by the high non-convexity of the underlying optimization process in BMD, which leads to extreme sensitivity to the initial blur kernel. To address this issue, we propose a novel framework for BMD that leverages a deep generative model to encode the kernel prior and induce a better initialization for the blur kernel. Specifically, we pre-train a kernel generator based on a generative adversarial network (GAN) to aptly characterize the kernel's prior distribution, as well as a kernel initializer to provide a well-informed and high-quality starting point for kernel estimation. By combining these two components, we constrain the BMD solution within a compact latent kernel manifold, thus alleviating the aforementioned sensitivity for kernel initialization. Notably, the kernel generator and initializer are designed to be easily integrated with existing BMD methods in a plug-and-play manner, enhancing their overall performance. Furthermore, we extend our approach to tackle blind non-uniform motion deblurring without the need for additional priors, achieving state-of-the-art performance on challenging benchmark datasets. The source code is available at https://github.com/dch0319/GLKM-Deblur.

Related papers

• Scalable Gaussian Processes with Low-Rank Deep Kernel Decomposition [7.532273334759435]
  Kernels are key to encoding prior beliefs and data structures in Gaussian process (GP) models.<n>Deep kernel learning enhances kernel flexibility by feeding inputs through a neural network before applying a standard parametric form.<n>We introduce a fully data-driven, scalable deep kernel representation where a neural network directly represents a low-rank kernel.
  arXiv  Detail & Related papers  (2025-05-24T05:42:11Z)
• Blind Image Deconvolution by Generative-based Kernel Prior and Initializer via Latent Encoding [46.40894748268764]
  Blind image encoding is a classic yet challenging problem in the field of image processing. Recent advances in deep image prior (DBID) have motivated a series of methods that demonstrate a-generative approaches. We propose a new pre-generative approach that better considers the prior modeling, and a generative approach for blur kernels.
  arXiv  Detail & Related papers  (2024-07-20T09:23:56Z)
• Blind Super-Resolution via Meta-learning and Markov Chain Monte Carlo Simulation [46.5310645609264]
  We propose a Meta-learning and Markov Chain Monte Carlo based SISR approach to learn kernel priors from organized randomness. A lightweight network is adopted as kernel generator, and is optimized via learning from the MCMC simulation on random Gaussian distributions. A meta-learning-based alternating optimization procedure is proposed to optimize the kernel generator and image restorer.
  arXiv  Detail & Related papers  (2024-06-13T07:50:15Z)
• Meta-Learning Hypothesis Spaces for Sequential Decision-making [79.73213540203389]
  We propose to meta-learn a kernel from offline data (Meta-KeL) Under mild conditions, we guarantee that our estimated RKHS yields valid confidence sets. We also empirically evaluate the effectiveness of our approach on a Bayesian optimization task.
  arXiv  Detail & Related papers  (2022-02-01T17:46:51Z)
• Kernel Identification Through Transformers [54.3795894579111]
  Kernel selection plays a central role in determining the performance of Gaussian Process (GP) models. This work addresses the challenge of constructing custom kernel functions for high-dimensional GP regression models. We introduce a novel approach named KITT: Kernel Identification Through Transformers.
  arXiv  Detail & Related papers  (2021-06-15T14:32:38Z)
• Flow-based Kernel Prior with Application to Blind Super-Resolution [143.21527713002354]
  Kernel estimation is generally one of the key problems for blind image super-resolution (SR) This paper proposes a normalizing flow-based kernel prior (FKP) for kernel modeling. Experiments on synthetic and real-world images demonstrate that the proposed FKP can significantly improve the kernel estimation accuracy.
  arXiv  Detail & Related papers  (2021-03-29T22:37:06Z)
• End-to-end Kernel Learning via Generative Random Fourier Features [31.57596752889935]
  Random Fourier features (RFFs) provide a promising way for kernel learning in a spectral case. In this paper, we consider a one-stage process that incorporates the kernel learning and linear learner into a unifying framework.
  arXiv  Detail & Related papers  (2020-09-10T00:27:39Z)

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.