Affiliation:
1. Hangzhou Normal University, China
2. Nanjing University, China
3. University of Missouri–Kansas City, USA
Abstract
Learning-based post-processing methods generally produce neural models that are statistically optimal on their training datasets. These models, however, neglect intrinsic variations of local video content and may fail to process unseen content. To address this issue, this article proposes a content-aware approach for the post-processing of compressed videos. We develop a backbone network, called
BackboneFormer
, where a Fast Transformer using Separable Self-Attention, Spatial Attention, and Channel Attention is devised to support underlying feature embedding and aggregation. Furthermore, we introduce Meta-learning to strengthen BackboneFormer for better performance. Specifically, we propose Meta Post-Processing (Meta-PP) which leverages the Meta-learning framework to drive BackboneFormer to capture and analyze input video variations for spontaneous updating. Since the original frame is unavailable to the decoder, we devise a Compression Degradation Estimation model where a low-complexity neural model and classic operators are used collaboratively to estimate the compression distortion. The estimated distortion is then utilized to guide the BackboneFormer model for dynamic updating of weighting parameters. Experimental results demonstrate that the proposed BackboneFormer itself gains about 3.61% Bjøntegaard delta bit-rate reduction over Versatile Video Coding in the post-processing task and “BackboneFormer + Meta-PP” attains 4.32%, costing only 50K and 61K parameters, respectively. The computational complexity of MACs is 49k/pixel and 50k/pixel, which represents only about 16% of state-of-the-art methods having similar coding gains.
Funder
National Natural Science Foundation of China
National Undergraduate Training Program for Innovation and Entrepreneurship
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Networks and Communications,Hardware and Architecture
Reference61 articles.
1. Yuval Bahat, Netalee Efrat, and Michal Irani. 2017. Non-uniform blind deblurring by reblurring. In Proceedings of the IEEE International Conference on Computer Vision. 3286–3294.
2. G. Bjøntegaard. 2001. Calculation of average PSNR differences between RD-curves. In Proceedings of the 13th Meeting of the Video Coding Experts Group.
3. Pre-Trained Image Processing Transformer
4. Artistic style transfer with internal-external learning and contrastive learning;Chen Haibo;Advances in Neural Information Processing Systems,2021
5. Simple baselines for image restoration;Chen Liangyu;arXiv preprint arXiv:2204.04676,2022
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. A Reconfigurable Framework for Neural Network Based Video In-Loop Filtering;ACM Transactions on Multimedia Computing, Communications, and Applications;2024-03-08