Journal
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
Volume 32, Issue 7, Pages 4138-4149Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2021.3123621
Keywords
Image coding; Quantization (signal); Streaming media; Bit rate; Image restoration; Transform coding; Video recording; Quality enhancement; CBR compressed video; dual-domain restoration
Categories
Funding
- National Key Research and Development Program of China [2020YFB1406604]
- National Nature Science Foundation of China [62001146, 61931008, 61671196, 61701149, 61801157, 61971268, 61901145, 61901150, 61972123]
- National Natural Science Major Foundation of Research Instrumentation of PR China [61427808]
- Zhejiang Province Nature Science Foundation of China [LR17F030006, Q19F010030]
- 111 Project [D17019]
Ask authors/readers for more resources
This study proposes a model based on neural networks to enhance the quality of CBR compressed videos. By utilizing a dual-domain restoration module and a two-step quantization degradation estimation strategy, the degradation caused by compression is effectively reduced, while a multi-scale network is employed to address block distortion. The experimental results demonstrate that this method outperforms existing approaches in both CBR and CQP video enhancement tasks.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available