基于非局部变分自编码器的单幅图像内部分布测量
Single Image Internal Distribution Measurement Using Non-Local Variational Autoencoder
摘要:
基于深度学习的超分辨率方法已经显示出巨大的前景,特别是对于单图像超分辨率(SISR)任务。尽管性能有所提高,但这些方法由于依赖于大量数据进行模型训练而受到限制。此外,监督SISR解决方案依赖于局部邻域信息,仅关注用于重建低维图像的特征学习过程。此外,由于其受限制的接受领域,他们未能利用全球环境。为了应对这些挑战,本文提出了一种新的图像特定的解决方案,即非局部变分自动编码器(\texttt{NLVAE}),重建一个高分辨率(HR)图像从一个单一的低分辨率(LR)图像,而不需要任何事先训练。为了收获最大的细节,为各种接受区域和高品质的合成图像,\texttt{NLVAE}被引入作为一个自我监督的策略,重建高分辨率的图像,使用从非本地邻域解开的信息。在7个基准数据集上的实验结果证明了\texttt{NLVAE}模型的有效性。此外,我们提出的模型优于一些基线和国家的最先进的方法,通过广泛的定性和定量评估证实。
英文摘要:
Deep learning-based super-resolution methods have shown great promise, especially for single image super-resolution (SISR) tasks. Despite the performance gain, these methods are limited due to their reliance on copious data for model training. In addition, supervised SISR solutions rely on local neighbourhood information focusing only on the feature learning processes for the reconstruction of low-dimensional images. Moreover, they fail to capitalize on global context due to their constrained receptive field. To combat these challenges, this paper proposes a novel image-specific solution, namely non-local variational autoencoder (\texttt{NLVAE}), to reconstruct a high-resolution (HR) image from a single low-resolution (LR) image without the need for any prior training. To harvest maximum details for various receptive regions and high-quality synthetic images, \texttt{NLVAE} is introduced as a self-supervised strategy that reconstructs high-resolution images using disentangled information from the non-local neighbourhood. Experimental results from seven benchmark datasets demonstrate the effectiveness of the \texttt{NLVAE} model. Moreover, our proposed model outperforms a number of baseline and state-of-the-art methods as confirmed through extensive qualitative and quantitative evaluations.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。