Restoration-Aligned Generative Flow Models for Blind Motion Deblurring

TL;DR

DeblurFlow reformulates generative flow models for motion deblurring by aligning the flow trajectory with the residual error, enabling effective restoration with high fidelity and perceptual quality.

Contribution

The paper introduces DeblurFlow, a novel framework that aligns flow models with restoration objectives and employs residual decoding in a tailored latent space for efficient, high-quality deblurring.

Findings

Achieves PSNR of 33.69 dB with high fidelity.

Enhances perceptual quality with marginal PSNR reduction.

Reduces encoder-decoder cost by up to 9× using r-space.

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.