Layered Image Compression Using Scalable Auto-Encoder

Chuanmin Jia, Zhaoyi Liu, Yao Wang, Siwei Ma, Wen Gao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents a novel convolutional neural network (CNN) based image compression framework via scalable auto-encoder (SAE). Specifically, our SAE based deep image codec consists of hierarchical coding layers, each of which is an end-to-end optimized auto-encoder. The coarse image content and texture are encoded through the first (base) layer while the consecutive (enhance) layers iteratively code the pixel-level reconstruction errors between the original and former reconstructed images. The proposed SAE structure alleviates the need to train multiple models for different bit-rate points by recently proposed auto-encoder based codecs. The SAE layers can be combined to realize multiple rate points, or to produce a scalable stream. The proposed method has similar rate-distortion performance in the low-to-medium rate range as the state-of-the-art CNN based image codec (which uses different optimized networks to realize different bit rates) over a standard public image dataset. Furthermore, the proposed codec generates better perceptual quality in this bit rate range.

Original languageEnglish (US)
Title of host publicationProceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages431-436
Number of pages6
ISBN (Electronic)9781728111988
DOIs
StatePublished - Apr 22 2019
Event2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019 - San Jose, United States
Duration: Mar 28 2019Mar 30 2019

Publication series

NameProceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019

Conference

Conference2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019
CountryUnited States
CitySan Jose
Period3/28/193/30/19

Fingerprint

Image compression
Neural networks
Textures
Pixels

Keywords

  • CNN
  • end-to-end optimization
  • Image Compression
  • scalable auto-encoder

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing
  • Media Technology

Cite this

Jia, C., Liu, Z., Wang, Y., Ma, S., & Gao, W. (2019). Layered Image Compression Using Scalable Auto-Encoder. In Proceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019 (pp. 431-436). [8695403] (Proceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MIPR.2019.00087

Layered Image Compression Using Scalable Auto-Encoder. / Jia, Chuanmin; Liu, Zhaoyi; Wang, Yao; Ma, Siwei; Gao, Wen.

Proceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 431-436 8695403 (Proceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Jia, C, Liu, Z, Wang, Y, Ma, S & Gao, W 2019, Layered Image Compression Using Scalable Auto-Encoder. in Proceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019., 8695403, Proceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019, Institute of Electrical and Electronics Engineers Inc., pp. 431-436, 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019, San Jose, United States, 3/28/19. https://doi.org/10.1109/MIPR.2019.00087
Jia C, Liu Z, Wang Y, Ma S, Gao W. Layered Image Compression Using Scalable Auto-Encoder. In Proceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 431-436. 8695403. (Proceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019). https://doi.org/10.1109/MIPR.2019.00087
Jia, Chuanmin ; Liu, Zhaoyi ; Wang, Yao ; Ma, Siwei ; Gao, Wen. / Layered Image Compression Using Scalable Auto-Encoder. Proceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 431-436 (Proceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019).
@inproceedings{d9191abcd88f47968fd90cb96e964abe,
title = "Layered Image Compression Using Scalable Auto-Encoder",
abstract = "This paper presents a novel convolutional neural network (CNN) based image compression framework via scalable auto-encoder (SAE). Specifically, our SAE based deep image codec consists of hierarchical coding layers, each of which is an end-to-end optimized auto-encoder. The coarse image content and texture are encoded through the first (base) layer while the consecutive (enhance) layers iteratively code the pixel-level reconstruction errors between the original and former reconstructed images. The proposed SAE structure alleviates the need to train multiple models for different bit-rate points by recently proposed auto-encoder based codecs. The SAE layers can be combined to realize multiple rate points, or to produce a scalable stream. The proposed method has similar rate-distortion performance in the low-to-medium rate range as the state-of-the-art CNN based image codec (which uses different optimized networks to realize different bit rates) over a standard public image dataset. Furthermore, the proposed codec generates better perceptual quality in this bit rate range.",
keywords = "CNN, end-to-end optimization, Image Compression, scalable auto-encoder",
author = "Chuanmin Jia and Zhaoyi Liu and Yao Wang and Siwei Ma and Wen Gao",
year = "2019",
month = "4",
day = "22",
doi = "10.1109/MIPR.2019.00087",
language = "English (US)",
series = "Proceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "431--436",
booktitle = "Proceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019",

}

TY - GEN

T1 - Layered Image Compression Using Scalable Auto-Encoder

AU - Jia, Chuanmin

AU - Liu, Zhaoyi

AU - Wang, Yao

AU - Ma, Siwei

AU - Gao, Wen

PY - 2019/4/22

Y1 - 2019/4/22

N2 - This paper presents a novel convolutional neural network (CNN) based image compression framework via scalable auto-encoder (SAE). Specifically, our SAE based deep image codec consists of hierarchical coding layers, each of which is an end-to-end optimized auto-encoder. The coarse image content and texture are encoded through the first (base) layer while the consecutive (enhance) layers iteratively code the pixel-level reconstruction errors between the original and former reconstructed images. The proposed SAE structure alleviates the need to train multiple models for different bit-rate points by recently proposed auto-encoder based codecs. The SAE layers can be combined to realize multiple rate points, or to produce a scalable stream. The proposed method has similar rate-distortion performance in the low-to-medium rate range as the state-of-the-art CNN based image codec (which uses different optimized networks to realize different bit rates) over a standard public image dataset. Furthermore, the proposed codec generates better perceptual quality in this bit rate range.

AB - This paper presents a novel convolutional neural network (CNN) based image compression framework via scalable auto-encoder (SAE). Specifically, our SAE based deep image codec consists of hierarchical coding layers, each of which is an end-to-end optimized auto-encoder. The coarse image content and texture are encoded through the first (base) layer while the consecutive (enhance) layers iteratively code the pixel-level reconstruction errors between the original and former reconstructed images. The proposed SAE structure alleviates the need to train multiple models for different bit-rate points by recently proposed auto-encoder based codecs. The SAE layers can be combined to realize multiple rate points, or to produce a scalable stream. The proposed method has similar rate-distortion performance in the low-to-medium rate range as the state-of-the-art CNN based image codec (which uses different optimized networks to realize different bit rates) over a standard public image dataset. Furthermore, the proposed codec generates better perceptual quality in this bit rate range.

KW - CNN

KW - end-to-end optimization

KW - Image Compression

KW - scalable auto-encoder

UR - http://www.scopus.com/inward/record.url?scp=85065605547&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065605547&partnerID=8YFLogxK

U2 - 10.1109/MIPR.2019.00087

DO - 10.1109/MIPR.2019.00087

M3 - Conference contribution

AN - SCOPUS:85065605547

T3 - Proceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019

SP - 431

EP - 436

BT - Proceedings - 2nd International Conference on Multimedia Information Processing and Retrieval, MIPR 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -