Learned Regularizers and Geometry for Image Denoising
Learned Regularizers and Geometry for Image Denoising
复制标题
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Stacey Levine;Ryan M Cecil;M. Bertalmío
中科院分区：
文献类型：
--
作者：
Stacey Levine;Ryan M Cecil;M. Bertalmío
最近的图像去噪框架已经证明，从图像的一些几何特征的平滑版本恢复图像比直接对图像去噪更有效率。在图像质量度量以及精细细节的保留方面都可以发现改进。处理这些数据的挑战在于，为处理自然图像数据而开发的数学上合理的机制并不一定适用，而且这些数据本身可能表现得很差。在这项工作中，我们学习了“几何”或非线性高阶特征以及相应的正则化子。这些方法在图像质量指标和保留精细特征方面都优于最近基于模型的深度学习（DL）图像去噪方法。此外，所提出的方法，用于增强DL架构，通过将几何启发的功能的动机，并有可能反馈到数学上的声音模型，以解决各种问题，在图像处理。
Recent frameworks for image denoising have demonstrated that it can be more productive to recover an image from a smoothed version of some geometric feature of the image rather than denoise the image directly. Improvements can be found both with respect to image quality metrics as well as the preservation of fine details. The challenge in working with this data is that mathematically sound mechanisms developed for handling natural image data do not necessarily apply, and this data itself can be quite ill behaved. In this work we learn both ‘geometric’ or nonlinear higher order features and corresponding regularizers. These approaches show improvement over recent model-based deep learning (DL) image denoising methods both with respect to image quality metrics as well as the preservation of fine features. Furthermore, the proposed approach for enhancing DL architectures by incorporating geometrically-inspired features is motivated by and has the potential to feed back into mathematically sound models for solving a variety of problems in image processing.