基于内外混合图像先验与图像融合的DIP改进降噪模型

An Improved DIP Denoising Model Based on Internal and External Image Priors and Image Fusion

为提高无监督深度图像先验(DIP)降噪模型的降噪性能,该文提出了一种基于内外混合图像先验与图像融合的DIP改进降噪模型(IDIP),该模型由样本生成和样本融合两个相继执行的模块组成。在样本生成阶段,首先利用2个分别来自内部和外部先验且有代表性的降噪算法(模型)处理噪声图像以产生2张初始降噪图像。基于这2张初始降噪图像,使用空间随机混合器按照各自50%混合比例随机生成足够多的混合图像作为DIP降噪模型的第2目标图像并与第1目标图像(即噪声图像)构成双目标图像。然后,每次使用不同的随机输入和双目标图像,多次执行标准DIP降噪流程生成多张具有互补性的样本图像;在样本融合阶段,首先为了获得更好的随机性和稳定性,随机丢弃50%的样本图像。然后,采用无监督融合网络在样本图像上完成自适应融合,获得的融合图像的图像质量相对参与融合的样本图像得到再次提升,作为最终降噪图像。在人工合成噪声图像上实验表明:IDIP降噪模型较原DIP降噪模型在峰值信噪比评价指标上有约2 dB的提升,且较大幅度超过了其他无监督降噪模型,逼近了有监督降噪模型。而在实际真实噪声图像上,其降噪性能较各对比方法更具鲁棒性。

To enhance the denoising performance of an unsupervised Deep Image Prior(DIP)model,an improved approach known as the Improved Deep Image Prior(IDIP)is proposed,which comprises sample generation and sample fusion modules,and leverages a prior hybrid image that combines internal and external factors,along with image fusion techniques.In the sample generation module,two representative denoising models are utilized,which capture internal and external priors and process the noisy image to produce two initial denoised images.Subsequently,a spatially random mixer is implemented on these initial denoised images to generate a sufficient number of mixed images.These mixed images,along with the noisy image,form dual-target images with a 50%mixing ratio.Furthermore,executing the standard DIP denoising process multiple times with different random inputs and dual-target images generates a set of diverse sample images with complementary characteristics.In the sample fusion module,to enhance randomness and stability,50%of the sample images are randomly discarded using dropout.Next,an unsupervised fusion network is used,which performs adaptive fusion on the remaining sample images.The resulting fused image exhibits improved image quality compared to the individual sample images and serves as the final denoised output.The experimental results on artificially generated noisy images reveal that the IDIP model is effective,with an improvement of approximately 2 dB in terms of Peak Signal-to-Noise Ratio(PSNR)compared to the original DIP model.Moreover,the IDIP model outperforms other unsupervised denoising models by a significant margin and approaches the performance level of supervised denoising models.When evaluated on real-world noisy images,the IDIP model exhibits superior denoising performance to the compared methods,thus verifying its robustness.