无需训练数据，用隐式表示修复模糊、降采样等混合退化的图像。
MG-SpaIR: Multi-grade Sparse-guided Implicit Representation for Training-Data-Free Image Restoration
- 分多级粗到细的残差结构，逐步提升重建精度。
- 引入显式稀疏正则化，抑制高频伪影并保留边缘细节。
- 适合无训练数据场景，结果稳定可解释，效率高。
MG-SpaIR 是一种无需训练数据的图像恢复框架，可从单一受混合退化（包括模糊、降采样、噪声和缺失像素）污染的观测中还原清晰图像。基于隐式神经表示（INRs），提出多级从粗到细的残差层次结构，逐级提升重建保真度并缓解频谱局限性。为稳定优化过程并抑制 INR 诱发的伪影，进一步在高分辨率图像域中引入显式稀疏近端正则化（如 $\\'ell_0$-型），有效抑制虚假高频模式，同时保持锐利结构。通过多级近端交替方案高效求解优化问题，并在标准正则条件下建立更新的收敛性保证。在混合退化基准上的实验表明，MG-SpaIR 持续优于 Deep Image Prior 等强基线方法，为传统学习型恢复方法提供了一种稳定、可解释且数据高效的替代方案。
原文摘要 · Abstract (English)
MG-SpaIR is a training-data-free framework for restoring a clean image from a single observation corrupted by a mixture of blur, downsampling, noise, and missing pixels. Building on implicit neural representations (INRs), we introduce a multi-grade coarse-to-fine residual hierarchy that progressively refines the reconstruction across resolution grades, improving representational fidelity and mitigating spectral limitations. To stabilize reconstruction optimization and suppress INR-induced artifacts, we further propose an explicit sparse proximal regularization (e.g., $\ell_0$-type) applied directly in the high-resolution image domain, which discourages spurious high-frequency patterns while preserving sharp structures. The resulting optimization is solved efficiently via a multi-grade proximal alternating scheme, and we establish convergence guarantees for the associated updates under standard regularity conditions. Experiments on mixed-degradation benchmarks demonstrate that MG-SpaIR consistently outperforms strong training-data-free baselines such as Deep Image Prior, providing a stable, interpretable, and data-efficient alternative to conventional learning-based restoration methods.
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。