Spatiotemporal Symmetric Convolutional Neural Network for Video Bit-Depth Enhancement
- 6 February 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 21 (9) , 2397-2406
Abstract
In contrast to the high sensitivity of human eyes and rapid development of modern display devices in terms of dynamic range, mainstream multimedia sources are generally at relatively lower bit depths (BDs). Therefore, BD enhancement (BDE), which attempts to transform low-BD multimedia sources into high-BD sources, is considered of significant research value. Current BDE algorithms are based on images rather than videos. However, for massive numbers of videos, temporal continuity among frames should be considered. Thus, in this paper, we propose a spatiotemporal symmetric BDE network for videos based on an encoder-decoder network. Consecutive frames are input into five subnets in the encoder, where the convolutional filters in the temporal symmetric subnets share the same weights to achieve lower model complexity. In addition, symmetric skip connections are introduced between the symmetric convolutional/deconvolutional layers of the encoder/decoder to pass features and alleviate the gradient diffusion problem. The experimental results show that our model can efficiently eliminate false contours and chroma distortions. The model significantly outperforms state-of-the-art image BDE algorithms and single-frame baseline models in terms of PSNR and SSIM.Keywords
Funding Information
- China Postdoctoral Science Foundation (2018M641648)
- National Science Foundation of China (61701341, 61572356, 61802277)
This publication has 27 references indexed in Scilit:
- Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network2016
- Image Bit-Depth Enhancement via Maximum A Posteriori Estimation of AC SignalIEEE Transactions on Image Processing, 2016
- Video Super-Resolution With Convolutional Neural NetworksIEEE Transactions on Computational Imaging, 2016
- Video Super-Resolution via Deep Draft-Ensemble Learning2015
- Hierarchical Convolutional Features for Visual Tracking2015
- Caffe2014
- Bit-depth expansion using Minimum Risk Based Classification2012
- From 2D Extrapolation to 1D Interpolation: Content Adaptive Image Bit-Depth Expansion2012
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004
- Pixel bit-depth increase by bit replication1998