Diffusion models (DMs) have recently been introduced in image deblurring and exhibited promising performance, particularly in terms of details reconstruction. However, the diffusion model requires a large number of inference iterations to recover the clean image from pure Gaussian noise, which consumes massive computational resources. Moreover, the distribution synthesized by the diffusion model is often misaligned with the target results, leading to restrictions in distortion-based metrics. To address the above issues, we propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring. Specifically, we perform the DM in a highly compacted latent space to generate the prior feature for the deblurring process. The deblurring process is implemented by a regression-based method to obtain better distortion accuracy. Meanwhile, the highly compact latent space ensures the efficiency of the DM. Furthermore, we design the hierarchical integration module to fuse the prior into the regression-based model from multiple scales, enabling better generalization in complex blurry scenarios. Comprehensive experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods. Code and trained models are available at https://github.com/zhengchen1999/HI-Diff.

翻译：最近，扩散模型已被应用于图像去模糊任务，并在细节重建方面展现出优异性能。然而，扩散模型需要大量推理迭代才能从纯高斯噪声中恢复清晰图像，这消耗了巨大的计算资源。此外，扩散模型合成的分布往往与目标结果存在偏差，导致基于失真的评估指标受限。针对上述问题，我们提出面向真实图像去模糊的分层融合扩散模型（HI-Diff）。具体而言，我们将扩散模型部署在高度压缩的潜在空间中，为去模糊过程生成先验特征。去模糊过程则采用基于回归的方法实现，以获得更优的失真精度。同时，高度压缩的潜在空间确保了扩散模型的效率。此外，我们设计了分层融合模块，将先验信息从多尺度融入回归模型中，从而在复杂模糊场景下实现更好的泛化能力。在合成和真实模糊数据集上的综合实验表明，我们的HI-Diff优于现有最优方法。代码和训练模型已开源至https://github.com/zhengchen1999/HI-Diff。