Paper Info
Title
Variable-Rate Multi-Frequency Image Compression using Modulated Generalized Octave Convolution
Abstract
In this proposal, we design a learned multi-frequency image compression approach that uses generalized octave convolutions to factorize the latent representations into high-frequency (HF) and low-frequency (LF) components, and the LF components have lower resolution than HF components, which can improve the rate-distortion performance, similar to wavelet transform. Moreover, compared to the original octave convolution, the proposed generalized octave convolution (GoConv) and octave transposed-convolution (GoTConv) with internal activation layers preserve more spatial structure of the information, and enable more effective filtering between the HF and LF components, which further improve the performance. In addition, we develop a variable-rate scheme using the Lagrangian parameter to modulate all the internal feature maps in the autoencoder, which allows the scheme to achieve the large bitrate range of the JPEG AI with only three models. Experiments show that the proposed scheme achieves much better Y MS-SSIM than VVC. In terms of YUV PSNR, our scheme is very similar to HEVC.
Year
DOI
Venue
2020
10.1109/MMSP48831.2020.9287082
2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)
Keywords
DocType
ISSN
learned image compression,octave convolution,variable-rate deep learning models,modulated scheme
Conference
2163-3517
ISBN
Citations 
PageRank 
978-1-7281-9323-6
0
0.34
References 
Authors
2
10
Name
Order
Citations
PageRank
Jianping Lin100.34
Mohammad Akbari24711.86
Haisheng Fu311.98
Qian Zhang41721.63
Shang Wang5306.48
Jie Liang670780.89
Dong Liu772174.92
Feng Liang843.05
Guohe Zhang9248.10
Chengjie Tu10768.46