WilmerHale, LLP, 60 State Street, Boston, MA 02139, USA.
IEEE Trans Pattern Anal Mach Intell. 2012 Apr;34(4):683-94. doi: 10.1109/TPAMI.2011.166.
The restoration of a blurry or noisy image is commonly performed with a MAP estimator, which maximizes a posterior probability to reconstruct a clean image from a degraded image. A MAP estimator, when used with a sparse gradient image prior, reconstructs piecewise smooth images and typically removes textures that are important for visual realism. We present an alternative deconvolution method called iterative distribution reweighting (IDR) which imposes a global constraint on gradients so that a reconstructed image should have a gradient distribution similar to a reference distribution. In natural images, a reference distribution not only varies from one image to another, but also within an image depending on texture. We estimate a reference distribution directly from an input image for each texture segment. Our algorithm is able to restore rich mid-frequency textures. A large-scale user study supports the conclusion that our algorithm improves the visual realism of reconstructed images compared to those of MAP estimators.
从降质图像重建清晰图像的常用方法是 MAP 估计，它通过最大化后验概率来实现。当 MAP 估计器与稀疏梯度图像先验结合使用时，它会重建分段平滑的图像，并且通常会去除对于视觉真实感很重要的纹理。我们提出了一种称为迭代分布重新加权（IDR）的替代去卷积方法，该方法对梯度施加全局约束，以便重建图像的梯度分布应类似于参考分布。在自然图像中，参考分布不仅因图像而异，而且还因纹理而异。我们为每个纹理段直接从输入图像估计参考分布。我们的算法能够恢复丰富的中频纹理。大规模的用户研究支持这样的结论：与 MAP 估计器相比，我们的算法能够提高重建图像的视觉真实感。
