Super-resolving Noisy Images
Super-resolving Noisy Images
复制标题
DOI：
10.1109/cvpr.2014.364
复制
发表时间：
2014-06
期刊：
影响因子：
--
通讯作者：
Abhishek Singh;F. Porikli;N. Ahuja
中科院分区：
文献类型：
--
作者：
Abhishek Singh;F. Porikli;N. Ahuja
我们的目标是从观察到的、有噪声的低分辨率(LR)图像中获得无噪声的高分辨率(HR)图像。用去噪算法对图像进行预处理，然后应用超分辨率(SR)算法的传统方法有一个重要的局限性：在去噪步骤中，图像中的一些高频内容(特别是纹理细节)总是会随着噪声一起丢失。这种去噪损失限制了后续SR步骤的性能，其中的挑战是合成这样的纹理细节。在本文中，我们证明了利用噪声图像中的高频成分(通常通过去噪算法去除)可以有效地在HR域中获得缺失的纹理细节。为此，我们首先使用基于块相似度的SR算法获得噪声图像和去噪图像的HR版本。然后，我们证明，通过取有噪和去噪的HR图像的方向和频率选择频带的凸组合，我们可以获得期望的HR图像，其中(I)在去噪步骤中丢失的一些纹理信号在HR域中得到有效恢复，以及(Ii)通过适当地约束凸组合的参数可以很容易地合成额外的纹理。我们表明，通过我们的算法对纹理的这种部分恢复和部分合成产生的HR图像比使用传统处理流水线获得的图像在视觉上更令人满意。此外，我们的结果显示在数值度量方面有持续的改进，进一步证实了我们的算法恢复丢失信号的能力。
Our goal is to obtain a noise-free, high resolution (HR) image, from an observed, noisy, low resolution (LR) image. The conventional approach of preprocessing the image with a denoising algorithm, followed by applying a super-resolution (SR) algorithm, has an important limitation: Along with noise, some high frequency content of the image (particularly textural detail) is invariably lost during the denoising step. This 'denoising loss' restricts the performance of the subsequent SR step, wherein the challenge is to synthesize such textural details. In this paper, we show that high frequency content in the noisy image (which is ordinarily removed by denoising algorithms) can be effectively used to obtain the missing textural details in the HR domain. To do so, we first obtain HR versions of both the noisy and the denoised images, using a patch-similarity based SR algorithm. We then show that by taking a convex combination of orientation and frequency selective bands of the noisy and the denoised HR images, we can obtain a desired HR image where (i) some of the textural signal lost in the denoising step is effectively recovered in the HR domain, and (ii) additional textures can be easily synthesized by appropriately constraining the parameters of the convex combination. We show that this part-recovery and part-synthesis of textures through our algorithm yields HR images that are visually more pleasing than those obtained using the conventional processing pipeline. Furthermore, our results show a consistent improvement in numerical metrics, further corroborating the ability of our algorithm to recover lost signal.