QQ客服 官方微博 反馈留言

	Deep Convolutional Network based Image Quality Enhancement for Low Bit Rate Image Compression
	Jia, Chuanmin ; Zhang, Xiang ; Zhang, Jian ; Wang, Shiqi ; Ma, Siwei
	2016
关键词	Low Bit Rate Image Compression Deep Convolutional Network
英文摘要	In this contribution, a novel image quality enhancement algorithm based on convolutional network is proposed for low bit rate image compression. Specifically, a downsample procedure is performed to generate lower resolution image for low bit rate compression. While the decoder side, upsample is to be performed firstly to the original resolution. Image quality is further enhanced by the proposed convolutional deep network. In particular, an optional image quality improvement network can be utilized for further enhancement after the first network. With the help of deep network, more detailed and high-frequency information can be recovered while maintaining the consistency of contour area, leading to better visual quality. Another benefit of this approach lies in that the proposed approach is fully compatible with all third-party image codec pipeline. Experimental result shows that the proposed scheme significantly outperforms JPEG in low bit rate image compression.; National Basic Research Program of China (973 Program) [2015CB351800]; National Natural Science Foundation of China [61322106, 61421062]; Shenzhen Peacock Plan; CPCI-S(ISTP); cmjia@pku.edu.cn; x_zhang@pku.edu.cn; jian.zhang@pku.edu.cn; swma@pku.edu.cn; wangshiqi@ntu.edu.sg
语种	英语
出处	30th IEEE Conference on Visual Communications and Image Processing (VCIP)
内容类型	其他
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/459676]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Jia, Chuanmin,Zhang, Xiang,Zhang, Jian,et al. Deep Convolutional Network based Image Quality Enhancement for Low Bit Rate Image Compression. 2016-01-01.

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。