Restoration-Aligned Generative Flow Models for Blind Motion Deblurring

• URL: http://arxiv.org/abs/2605.08854v1
• Date: Sat, 09 May 2026 10:05:51 GMT
• Title: Restoration-Aligned Generative Flow Models for Blind Motion Deblurring
• Abstract summary: We present DeFlow, a framework that resolves misalignment by reformulating the flow trajectory itself.<n>Under this formulation, the standard flow matching loss naturally takes the form of a residual loss.<n>Experiments on GoPro, HIDE, RealBlur, and RWBI demonstrate that DeFlow achieves strong restoration fidelity and perceptual realism.
• Score: 57.425021485907756
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative flow models offer powerful priors learned from large-scale natural images, but directly adapting them to restoration tasks such as motion deblurring causes severe fidelity degradation, as their training objective is inherently misaligned with restoration. We present DeblurFlow, a framework that resolves this misalignment by reformulating the flow trajectory itself: we replace the noise endpoint with the blur observation, which makes the underlying vector field coincide with the residual error between blur and clean images. Under this formulation, the standard flow matching loss naturally takes the form of a residual loss, allowing pretrained flow models to be optimized under restoration-aligned objectives via LoRA adaptation. This formulation further enables a dual-expert sampling strategy: a fidelity expert provides a high-fidelity initialization, e.g., PSNR 33.69 dB, and DeblurFlow enhances perceptual quality with only a marginal fidelity reduction to 33.05 dB, whereas directly applying a generative model on top of a fidelity expert decreases PSNR to 27.60 dB. To make this practical, we further introduce r-space, a latent space tailored for residual decoding rather than image reconstruction, which reduces encoder-decoder cost by up to 9$\times$over standard VAE latents. Extensive experiments on GoPro, HIDE, RealBlur, and RWBI demonstrate that DeblurFlow achieves strong restoration fidelity and perceptual realism, while remaining computationally practical.

Related papers

• Restore What Matters: Lessons from Joint Restoration and Recognition [72.91692240810536]
  Recognition pipelines typically adopt a restore-then-recognize workflow, yet decades of experience show that generating visually pleasing images seldom to improved recognition.<n>We propose a Joint Restoration-for-Recognition paradigm: restore only what downstream tasks truly require, with task signals dictating where, how much, and whether restoration is necessary.<n>We conclude that better-looking images are neither necessary nor sufficient; restoration modules must be task-driven, selective, and physically aware.
  arXiv  Detail & Related papers  (2026-09-12T08:08:08Z)
• Flow Straight to Reality: Perceptually Consistent Flow Matching for Efficient Image Restoration [3.901664292361698]
  PCFlow is a unified framework that parameterizes a continuous transport from degraded observations to clean targets.<n>It achieves competitive performance across diverse restoration tasks at a fraction of traditional computational costs.
  arXiv  Detail & Related papers  (2026-08-11T06:37:10Z)
• FDIR: Harmonizing Fidelity and Human-Machine Preference in Lossy Compression Image Restoration [3.7323617838648566]
  Flow-Conditioned Detail Refinement (FCDR) deterministically restores high-frequency textures and suppresses generative hallucinations in pixel space.<n>FDIR achieves superior fidelity, with a favorable perceptual-fidelity balance and competitive machine preference.
  arXiv  Detail & Related papers  (2026-07-31T08:33:40Z)
• ScaleResfusion: Residual Rectified Flow based on Residual Vector Field [24.544037828084154]
  Real-world Image Restoration (Real-IR) aims to recover high-quality (HQ) images from complex and unknown degradations.<n>Recent diffusion-based methods have substantially improved perceptual quality, but their current designs leave two key challenges unresolved.<n>We present ScaleResfusion, a scalable diffusion framework for real-world image restoration built on pre-trained text-to-image rectified-flow models.
  arXiv  Detail & Related papers  (2026-07-28T04:26:05Z)
• IR-Flow: Bridging Discriminative and Generative Image Restoration via Rectified Flow [46.532530550015736]
  We propose IR-Flow, a novel image restoration method based on Rectified Flow.<n>We first construct multilevel data distribution flows, which expand the ability of models to learn from and adapt to various levels of degradation.<n>We show that directly establishing a linear transport flow between degraded and clean image domains not only enables fast inference but also improves adaptability to out-of-distribution degradations.
  arXiv  Detail & Related papers  (2026-04-21T16:58:14Z)
• Harnessing Diffusion-Yielded Score Priors for Image Restoration [29.788482710572307]
  Deep image restoration models aim to learn a mapping from degraded image space to natural image space.<n>Three major classes of methods have emerged, including MSE-based, GAN-based, and diffusion-based methods.<n>We propose a novel method, HYPIR, to address these challenges.
  arXiv  Detail & Related papers  (2025-07-28T07:55:34Z)
• Solving Inverse Problems with FLAIR [68.87167940623318]
  We present FLAIR, a training-free variational framework that leverages flow-based generative models as prior for inverse problems.<n>Results on standard imaging benchmarks demonstrate that FLAIR consistently outperforms existing diffusion- and flow-based methods in terms of reconstruction quality and sample diversity.
  arXiv  Detail & Related papers  (2025-06-03T09:29:47Z)
• LAFR: Efficient Diffusion-based Blind Face Restoration via Latent Codebook Alignment Adapter [52.93785843453579]
  Blind face restoration from low-quality (LQ) images is a challenging task that requires high-fidelity image reconstruction and the preservation of facial identity.<n>We propose LAFR, a novel codebook-based latent space adapter that aligns the latent distribution of LQ images with that of HQ counterparts.<n>We show that lightweight finetuning of diffusion prior on just 0.9% of FFHQ dataset is sufficient to achieve results comparable to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-05-29T14:11:16Z)
• Latent Diffusion Prior Enhanced Deep Unfolding for Snapshot Spectral Compressive Imaging [17.511583657111792]
  Snapshot spectral imaging reconstruction aims to reconstruct three-dimensional spatial-spectral images from a single-shot two-dimensional compressed measurement. We introduce a generative model, namely the latent diffusion model (LDM), to generate degradation-free prior to deep unfolding method.
  arXiv  Detail & Related papers  (2023-11-24T04:55:20Z)
• Deep Equilibrium Diffusion Restoration with Parallel Sampling [120.15039525209106]
  Diffusion model-based image restoration (IR) aims to use diffusion models to recover high-quality (HQ) images from degraded images, achieving promising performance. Most existing methods need long serial sampling chains to restore HQ images step-by-step, resulting in expensive sampling time and high computation costs. In this work, we aim to rethink the diffusion model-based IR models through a different perspective, i.e., a deep equilibrium (DEQ) fixed point system, called DeqIR.
  arXiv  Detail & Related papers  (2023-11-20T08:27:56Z)
• Exploiting Diffusion Prior for Real-World Image Super-Resolution [75.5898357277047]
  We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution. By employing our time-aware encoder, we can achieve promising restoration results without altering the pre-trained synthesis model.
  arXiv  Detail & Related papers  (2023-05-11T17:55:25Z)

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.