arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2004.12811cs.CVcs.MMeess.IV
收藏

基于生成式变分自编码器的无监督真实图像超分辨率

Unsupervised Real Image Super-Resolution via Generative Variational AutoEncoder

The Hong Kong Polytechnic University(香港理工大学);École polytechnique(巴黎综合理工学院)

Zhi-Song Liu, Wan-Chi Siu, Li-Wen Wang, Chu-Tak Li, Marie-Paule Cani, Yui-Lam Chan

摘要:

受深度学习的影响,图像超分辨率已成为计算机视觉中最具发展前景的研究领域之一。取决于是否使用卷积器,深度卷积神经网络可以提供具有高保真度或更好感知质量的图像。由于在现实生活中缺乏地面真实图像,人们更喜欢具有低保真度的照片级真实图像,而不是具有高保真度的模糊图像。在本文中,我们回顾了经典的基于示例的图像超分辨率方法,并提出了一种新的生成模型的感知图像超分辨率。针对真实图像中存在的各种噪声和伪影,提出了一种基于变分自编码器的图像去噪和超分辨率联合模型。我们提出了一个条件变分自编码器来编码稠密特征向量的参考,然后将其传输到解码器进行目标图像去噪。该算法通过增加一个额外的超分辨率子网络开销,实现了去噪后图像的超分辨率化,并具有逼真的视觉效果。我们参加了NTIRE2020 Real Image超分辨率挑战赛。实验结果表明,通过使用该方法,我们可以获得放大图像与其他监督方法相比,清洁和愉快的功能。我们还在各种数据集上将我们的方法与最先进的方法进行了比较,以证明我们提出的无监督超分辨率模型的效率。

英文摘要:

Benefited from the deep learning, image Super-Resolution has been one of the most developing research fields in computer vision. Depending upon whether using a discriminator or not, a deep convolutional neural network can provide an image with high fidelity or better perceptual quality. Due to the lack of ground truth images in real life, people prefer a photo-realistic image with low fidelity to a blurry image with high fidelity. In this paper, we revisit the classic example based image super-resolution approaches and come up with a novel generative model for perceptual image super-resolution. Given that real images contain various noise and artifacts, we propose a joint image denoising and super-resolution model via Variational AutoEncoder. We come up with a conditional variational autoencoder to encode the reference for dense feature vector which can then be transferred to the decoder for target image denoising. With the aid of the discriminator, an additional overhead of super-resolution subnetwork is attached to super-resolve the denoised image with photo-realistic visual quality. We participated the NTIRE2020 Real Image Super-Resolution Challenge. Experimental results show that by using the proposed approach, we can obtain enlarged images with clean and pleasant features compared to other supervised methods. We also compared our approach with state-of-the-art methods on various datasets to demonstrate the efficiency of our proposed unsupervised super-resolution model.

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。

↑