当前位置: X-MOL 学术Signal Process. Image Commun. › 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 learning based HEVC in-loop filter and noise reduction
Signal Processing: Image Communication ( IF 3.4 ) Pub Date : 2021-08-20 , DOI: 10.1016/j.image.2021.116409
Shiba Kuanar 1, 2 , K.R. Rao 1 , Christopher Conly 3 , Ninad Gorey 1
Affiliation  

The lossy compression techniques at low bit rate often create ringing and contouring effects on the output images and introduce various blurring and distortion at block bounders. To overcome those compression artifacts different neural network based post-processing techniques have been experimented with over the last few years. The traditional loop-filter methods in the HEVC frame-work support two post-processing operations namely a de-blocking filter followed by a sample adaptive offset (SAO) filter. These operations usually introduce extra signaling bits and become overhead to the network with high-resolution video processing. In this study, we came up with a new deep learning-based algorithm for SAO filtering operations and substantiated the merits of the proposed method. We introduced a variable filter size sub-layered dense CNN (SDCNN) to improve the denoising operation and incorporated large stride deconvolution layers for further computation improvement. We demonstrate that our deconvolution model can effectively be trained by leveraging the high-frequency edge features learned in a shallow network using residual learning and data augmentation techniques. Extensive experiments show that our approach outperformed other state-of-the-art approaches in terms of SSIM, Bjøntegaard delta bit-rate (BD-BR), BD-PSNR measurements on the standard video test set and achieves an average of 8.73 % bit rate saving compared to HEVC baseline.



中文翻译:

基于深度学习的 HEVC 环路滤波器和降噪

低比特率的有损压缩技术通常会在输出图像上产生振铃和轮廓效果,并在块边界处引入各种模糊和失真。为了克服这些压缩伪影,在过去几年中已经尝试了不同的基于神经网络的后处理技术。HEVC 框架中的传统环路滤波器方法支持两种后处理操作,即去块滤波器后跟样本自适应偏移 (SAO) 滤波器。这些操作通常会引入额外的信令位并成为具有高分辨率视频处理的网络的开销。在这项研究中,我们提出了一种新的基于深度学习的 SAO 过滤操作算法,并证实了所提出方法的优点。我们引入了一个可变滤波器大小的子层密集 CNN (SDCNN) 来改进去噪操作,并结合大步幅去卷积层以进一步改进计算。我们证明了我们的反卷积模型可以通过利用在浅层网络中使用残差学习和数据增强技术学习的高频边缘特征进行有效训练。大量实验表明,我们的方法在 SSIM、Bjøntegaard delta 比特率 (BD-BR)、标准视频测试集上的 BD-PSNR 测量方面优于其他最先进的方法,平均达到 8.73% 比特与 HEVC 基线相比节省了速率。我们证明了我们的反卷积模型可以通过利用在浅层网络中使用残差学习和数据增强技术学习的高频边缘特征进行有效训练。大量实验表明,我们的方法在 SSIM、Bjøntegaard delta 比特率 (BD-BR)、标准视频测试集上的 BD-PSNR 测量方面优于其他最先进的方法,平均达到 8.73% 比特与 HEVC 基线相比节省了速率。我们证明了我们的反卷积模型可以通过利用在浅层网络中使用残差学习和数据增强技术学习的高频边缘特征进行有效训练。大量实验表明,我们的方法在 SSIM、Bjøntegaard delta 比特率 (BD-BR)、标准视频测试集上的 BD-PSNR 测量方面优于其他最先进的方法,平均达到 8.73% 比特与 HEVC 基线相比节省了速率。

更新日期:2021-09-01
down
wechat
bug