论文标题
贝叶斯图像超分辨率具有图像统计的深层建模
Bayesian Image Super-Resolution with Deep Modeling of Image Statistics
论文作者
论文摘要
图像先验的建模统计数据对于图像超分辨率很有用，但是从基于深度学习的方法的大量工作中，很少有人关注。在这项工作中，我们提出了一个贝叶斯图像恢复框架，其中自然图像统计数据是通过平滑度和稀疏性先验的组合建模的。具体而言，首先，我们将理想的图像视为平滑度成分和稀疏性残留的总和，并模型真实的图像降级，包括模糊，降低缩放和噪声腐败。然后，我们开发了一种跨性别贝叶斯的方法来推断其后代。最后，我们使用深神经网络实施了单图超分辨率（SISR）的变分方法，并提出了无监督的训练策略。对三个图像恢复任务的实验，\ textit {i。代码和结果模型通过\ url {https://zmiclab.github.io/projects.html}发布。
Modeling statistics of image priors is useful for image super-resolution, but little attention has been paid from the massive works of deep learning-based methods. In this work, we propose a Bayesian image restoration framework, where natural image statistics are modeled with the combination of smoothness and sparsity priors. Concretely, firstly we consider an ideal image as the sum of a smoothness component and a sparsity residual, and model real image degradation including blurring, downscaling, and noise corruption. Then, we develop a variational Bayesian approach to infer their posteriors. Finally, we implement the variational approach for single image super-resolution (SISR) using deep neural networks, and propose an unsupervised training strategy. The experiments on three image restoration tasks, \textit{i.e.,} ideal SISR, realistic SISR, and real-world SISR, demonstrate that our method has superior model generalizability against varying noise levels and degradation kernels and is effective in unsupervised SISR. The code and resulting models are released via \url{https://zmiclab.github.io/projects.html}.
