无需重训练，一模型搞定多种图像逆问题修复。
Zero-Shot Solving of Imaging Inverse Problems via Noise-Refined Likelihood Guided Diffusion Models
- 通过噪声精炼的似然引导机制，高效估算梯度避免复杂计算。
- 在5%采样率下压缩感知重建仍保持高质量，性能领先。
- 适配多种修复场景，适合快速部署于未知退化环境。
扩散模型因其强大的生成能力，在图像逆问题中取得了显著进展。然而，现有方法通常依赖针对特定退化类型训练的模型，难以泛化到多种退化场景。为此，我们提出一种零样本框架，可在不重新训练模型的情况下处理多种图像逆问题。引入似然引导的噪声精炼机制，推导出似然梯度的闭式近似，简化梯度估计并避免昂贵的梯度计算。该估计梯度用于精炼模型预测的噪声，使修复过程更契合扩散模型的生成框架。此外，融合去噪扩散隐式模型（DDIM）采样策略，进一步提升推理效率。所提机制可应用于基于优化和基于采样的两种方案，为图像逆问题提供高效灵活的零样本解决方案。大量实验表明，该方法在多个逆问题上表现优异，尤其在压缩感知任务中，即使在5%极低采样率下也能实现高质量重建。
原文摘要 · Abstract (English)
Diffusion models have achieved remarkable success in imaging inverse problems owing to their powerful generative capabilities. However, existing approaches typically rely on models trained for specific degradation types, limiting their generalizability to various degradation scenarios. To address this limitation, we propose a zero-shot framework capable of handling various imaging inverse problems without model retraining. We introduce a likelihood-guided noise refinement mechanism that derives a closed-form approximation of the likelihood score, simplifying score estimation and avoiding expensive gradient computations. This estimated score is subsequently utilized to refine the model-predicted noise, thereby better aligning the restoration process with the generative framework of diffusion models. In addition, we integrate the Denoising Diffusion Implicit Models (DDIM) sampling strategy to further improve inference efficiency. The proposed mechanism can be applied to both optimization-based and sampling-based schemes, providing an effective and flexible zero-shot solution for imaging inverse problems. Extensive experiments demonstrate that our method achieves superior performance across multiple inverse problems, particularly in compressive sensing, delivering high-quality reconstructions even at an extremely low sampling rate (5%).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。