Multi-Modality Deep Restoration of Extremely Compressed Face Videos
- 8 March 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (2) , 2024-2037
Abstract
Arguably the most common and salient object in daily video communications is the talking head, as encountered in social media, virtual classrooms, teleconferences, news broadcasting, talk shows, etc. When communication bandwidth is limited by network congestions or cost effectiveness, compression artifacts in talking head videos are inevitable. The resulting video quality degradation is highly visible and objectionable due to high acuity of human visual system to faces. To solve this problem, we develop a multi-modality deep convolutional neural network method for restoring face videos that are aggressively compressed. The main innovation is a new DCNN architecture that incorporates known priors of multiple modalities: the video-synchronized speech signal and semantic elements of the compression code stream, including motion vectors, code partition map and quantization parameters. These priors strongly correlate with the latent video and hence they are able to enhance the capability of deep learning to remove compression artifacts. Ample empirical evidences are presented to validate the superior performance of the proposed DCNN method on face videos over the existing state-of-the-art methods.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China
- Natural Sciences and Engineering Research Council of Canada
This publication has 64 references indexed in Scilit:
- Postprocessing of Compressed Images via Sequential DenoisingIEEE Transactions on Image Processing, 2016
- Data-Driven Soft Decoding of Compressed Images in Dual Transform-Pixel DomainIEEE Transactions on Image Processing, 2016
- Compression Artifacts Reduction by a Deep Convolutional Network2015
- Compression Artifact Reduction by Overlapped-Block Transform Coefficient Estimation With Block SimilarityIEEE Transactions on Image Processing, 2013
- $\ell_{2}$ Restoration of $\ell_{\infty}$-Decoded Images Via Soft-Decision EstimationIEEE Transactions on Image Processing, 2012
- Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognitionSpeech Communication, 2012
- Pointwise Shape-Adaptive DCT for High-Quality Denoising and Deblocking of Grayscale and Color ImagesIEEE Transactions on Image Processing, 2007
- HMM-Based Audio Keyword Generation2004
- Voice puppetry1999
- The MPEG-4 video standard verification modelIEEE Transactions on Circuits and Systems for Video Technology, 1997