当前位置: X-MOL 学术arXiv.cs.CV › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Deep Attentive Generative Adversarial Network for Photo-Realistic Image De-Quantization
arXiv - CS - Computer Vision and Pattern Recognition Pub Date : 2020-04-07 , DOI: arxiv-2004.03150
Yang Zhang, Changhui Hu, and Xiaobo Lu

Most of current display devices are with eight or higher bit-depth. However, the quality of most multimedia tools cannot achieve this bit-depth standard for the generating images. De-quantization can improve the visual quality of low bit-depth image to display on high bit-depth screen. This paper proposes DAGAN algorithm to perform super-resolution on image intensity resolution, which is orthogonal to the spatial resolution, realizing photo-realistic de-quantization via an end-to-end learning pattern. Until now, this is the first attempt to apply Generative Adversarial Network (GAN) framework for image de-quantization. Specifically, we propose the Dense Residual Self-attention (DenseResAtt) module, which is consisted of dense residual blocks armed with self-attention mechanism, to pay more attention on high-frequency information. Moreover, the series connection of sequential DenseResAtt modules forms deep attentive network with superior discriminative learning ability in image de-quantization, modeling representative feature maps to recover as much useful information as possible. In addition, due to the adversarial learning framework can reliably produce high quality natural images, the specified content loss as well as the adversarial loss are back-propagated to optimize the training of model. Above all, DAGAN is able to generate the photo-realistic high bit-depth image without banding artifacts. Experiment results on several public benchmarks prove that the DAGAN algorithm possesses ability to achieve excellent visual effect and satisfied quantitative performance.

中文翻译:

用于逼真图像去量化的深度注意力生成对抗网络

大多数当前的显示设备具有八位或更高位深。然而,大多数多媒体工具的质量无法达到生成图像的这种位深标准。去量化可以提高低位深图像在高位深屏幕上显示的视觉质量。本文提出了 DAGAN 算法对与空间分辨率正交的图像强度分辨率进行超分辨率,通过端到端的学习模式实现照片般逼真的去量化。到目前为止,这是第一次尝试将生成对抗网络 (GAN) 框架应用于图像去量化。具体来说,我们提出了密集残差自注意力(DenseResAtt)模块,该模块由具有自注意力机制的密集残差块组成,以更加关注高频信息。而且,顺序 DenseResAtt 模块的串联形成深度注意力网络,在图像去量化方面具有卓越的判别学习能力,建模代表性特征图以尽可能多地恢复有用信息。此外,由于对抗性学习框架可以可靠地产生高质量的自然图像,指定的内容损失以及对抗性损失被反向传播以优化模型的训练。最重要的是,DAGAN 能够生成照片般逼真的高位深度图像,而不会产生条带伪影。在多个公开基准上的实验结果证明,DAGAN 算法具有实现出色视觉效果和令人满意的量化性能的能力。此外,由于对抗性学习框架可以可靠地产生高质量的自然图像,指定的内容损失以及对抗性损失被反向传播以优化模型的训练。最重要的是,DAGAN 能够生成照片般逼真的高位深度图像,而不会产生条带伪影。在多个公开基准上的实验结果证明,DAGAN 算法具有实现出色视觉效果和令人满意的量化性能的能力。此外,由于对抗性学习框架可以可靠地产生高质量的自然图像,指定的内容损失以及对抗性损失被反向传播以优化模型的训练。最重要的是,DAGAN 能够生成照片般逼真的高位深度图像,而不会产生条带伪影。在多个公开基准上的实验结果证明,DAGAN 算法具有实现出色视觉效果和令人满意的量化性能的能力。
更新日期:2020-04-08
down
wechat
bug