Stanley Osher 和Martin Burger提出的基于Bregman 距离的迭代正则化全变分去噪算法运算速度较快，但是应用于图像去噪时，没有考虑不同区域的灰度分布特性，从而容易导致纹理等重要信息丢失或模糊的缺陷。针对这一现象，提出了一种基于自适应正则化的全变分去噪算法。论文对Osher的去噪模型中的全局正则化参数进行改进，给出了一种根据图像中不同区域的灰度分布特性，自适应选取正则化参数的方法。该算法可以保留图像的边缘和纹理细节信息。实验结果证实了所提算法的有效性，其信噪比较原有方法至少提高1.0 dB以上。

Stanley Osher and Martin Burger introduced an iterative regularization method for image de-nosing based on the Bregman distance. The approach can improve the general procedure and save the execution time. However, important information, such as texture is often compromised in the process of de-noising. The reason is that the proposed approach ignored the gradient information of each pixel. In order to avoid the above phenomenon, a novel texture preserving variational de-noising method based on the use of adaptive regularization is proposed in this paper . The new adaptive regularization method based total variational de-noising algorithm uses an adaptive fidelity term which locally controls the extent of de-nosing over image regions according to the gradient information of each pixel. So important information, such as edge and texture is preserved. The numerical results for de-nosing show the improvement in the signal-to-noise ratio (SNR) over standard model processes, and they are visually more appealing.