CBREN: Convolutional Neural Networks for Constant Bit Rate Video Quality Enhancement
文献类型：期刊论文
| 作者 | Zhao, Hengrun3; Zheng, Bolun3; Yuan, Shanxin4; Zhang, Hua1; Yan, Chenggang3; Li, Liang5; Slabaugh, Gregory2 |
| 刊名 | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
 |
| 出版日期 | 2022-07-01 |
| 卷号 | 32期号:7页码:4138-4149 |
| 关键词 | Image coding Quantization (signal) Streaming media Bit rate Image restoration Transform coding Video recording Quality enhancement CBR compressed video dual-domain restoration |
| ISSN号 | 1051-8215 |
| DOI | 10.1109/TCSVT.2021.3123621 |
| 英文摘要 | Constant bit rate (CBR) videos are widely used in streaming playback applications. However, the image quality of the CBR video is often unstable, especially for scenes with large motion. To this end, we design a new model to represent the distortion of High Efficiency Video Coding (HEVC) constant bit rate video, and propose a neural network for a constant bit rate video quality enhancement (CBREN). We propose a dual-domain restoration module (DRM) to jointly learn the prior knowledge in the pixel domain and the frequency domain. To address the degradation resulting from compression, we propose a two-step quantization degradation estimation strategy. The Inverse DCT (IDCT) Translation Unit (ITU) is used to constrain the quantization table of the constant bit rate video to a suitable range, and the Dynamic Alpha Unit (DAU) is used to fine-tune the quantization table according to the content of each frame. In order to effectively reduce the block distortion of different sizes produced in the compression process, we adopt a multi-scale network. Extensive experiments show that our approach can greatly enhance the quality of CBR compressed video. Moreover, our method can also be applied to constant quantization parameter (CQP) video enhancement tasks, and is certainly superior to existing methods. |
| 资助项目 | National Key Research and Development Program of China[2020YFB1406604] ; National Nature Science Foundation of China[62001146] ; National Nature Science Foundation of China[61931008] ; National Nature Science Foundation of China[61671196] ; National Nature Science Foundation of China[61701149] ; National Nature Science Foundation of China[61801157] ; National Nature Science Foundation of China[61971268] ; National Nature Science Foundation of China[61901145] ; National Nature Science Foundation of China[61901150] ; National Nature Science Foundation of China[61972123] ; National Natural Science Major Foundation of Research Instrumentation of PR China[61427808] ; Zhejiang Province Nature Science Foundation of China[LR17F030006] ; Zhejiang Province Nature Science Foundation of China[Q19F010030] ; 111 Project[D17019] |
| WOS研究方向 | Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000819817700006 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/19520]  |
| 专题 | 中国科学院计算技术研究所期刊论文_英文 |
| 通讯作者 | Zheng, Bolun; Zhang, Hua |
| 作者单位 | 1.Hangzhou Dianzi Univ, Sch Comp Sci, Hangzhou 311305, Peoples R China 2.Queen Mary Univ London, Digital Environm Res Inst DERI, London E1 4NS, England 3.Hangzhou Dianzi Univ, Sch Automat, Hangzhou 311305, Peoples R China 4.Huawei Technol, Noahs Ark Lab, London N1C 4AG, England 5.Chinese Acad Sci, Inst Comp Technol, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhao, Hengrun,Zheng, Bolun,Yuan, Shanxin,et al. CBREN: Convolutional Neural Networks for Constant Bit Rate Video Quality Enhancement[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2022,32(7):4138-4149. |
| APA | Zhao, Hengrun.,Zheng, Bolun.,Yuan, Shanxin.,Zhang, Hua.,Yan, Chenggang.,...&Slabaugh, Gregory.(2022).CBREN: Convolutional Neural Networks for Constant Bit Rate Video Quality Enhancement.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,32(7),4138-4149. |
| MLA | Zhao, Hengrun,et al."CBREN: Convolutional Neural Networks for Constant Bit Rate Video Quality Enhancement".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 32.7(2022):4138-4149. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
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。