Paper Info
Title
Learned Multi-Resolution Variable-Rate Image Compression With Octave-Based Residual Blocks
Abstract
Recently deep learning-based image compression has shown the potential to outperform traditional codecs. However, most existing methods train multiple networks for multiple bit rates, which increase the implementation complexity. In this paper, we propose a new variable-rate image compression framework, which employs generalized octave convolutions (GoConv) and generalized octave transposed-convolutions (GoTConv) with built-in generalized divisive normalization (GDN) and inverse GDN (IGDN) layers. Novel GoConv- and GoTConv-based residual blocks are also developed in the encoder and decoder networks. Our scheme also uses a stochastic rounding-based scalar quantization. To further improve the performance, we encode the residual between the input and the reconstructed image from the decoder network as an enhancement layer. To enable a single model to operate with different bit rates and to learn multi-rate image features, a new objective function is introduced. Experimental results show that the proposed framework trained with variable-rate objective function outperforms the standard codecs such as H.265/HEVC-based BPG and state-of-the-art learning-based variable-rate methods.
Year
DOI
Venue
2021
10.1109/TMM.2021.3068523
IEEE TRANSACTIONS ON MULTIMEDIA
Keywords
DocType
Volume
Image coding, Decoding, Convolutional codes, Transforms, Codecs, Image reconstruction, Linear programming, Deep learning, generalized octave convolutions, image compression, residual coding, variable-rate
Journal
23
ISSN
Citations 
PageRank 
1520-9210
0
0.34
References 
Authors
0
4
Name
Order
Citations
PageRank
Mohammad Akbari14711.86
Jie Liang270780.89
Jingning Han316425.48
Chengjie Tu4768.46