TY - GEN
T1 - An End-To-End Compression Framework Based on Convolutional Neural Networks
AU - Tao, Wen
AU - Jiang, Feng
AU - Zhang, Shengping
AU - Ren, Jie
AU - Shi, Wuzhen
AU - Zuo, Wangmeng
AU - Guo, Xun
AU - Zhao, Debin
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/5/8
Y1 - 2017/5/8
N2 - Traditional image coding standards (such as JPEG and JPEG2000) make the decoded image suffer from many blocking artifacts or noises since the use of big quantization steps. To overcome this problem, we proposed an end-To-end compression framework based on two CNNs, as shown in Figure 1, which produce a compact representation for encoding using a third party coding standard and reconstruct the decoded image, respectively. To make two CNNs effectively collaborate, we develop a unified end-To-end learning framework to simultaneously learn CrCNN and ReCNN such that the compact representation obtained by CrCNN preserves the structural information of the image, which facilitates to accurately reconstruct the decoded image using ReCNN and also makes the proposed compression framework compatible with existing image coding standards.
AB - Traditional image coding standards (such as JPEG and JPEG2000) make the decoded image suffer from many blocking artifacts or noises since the use of big quantization steps. To overcome this problem, we proposed an end-To-end compression framework based on two CNNs, as shown in Figure 1, which produce a compact representation for encoding using a third party coding standard and reconstruct the decoded image, respectively. To make two CNNs effectively collaborate, we develop a unified end-To-end learning framework to simultaneously learn CrCNN and ReCNN such that the compact representation obtained by CrCNN preserves the structural information of the image, which facilitates to accurately reconstruct the decoded image using ReCNN and also makes the proposed compression framework compatible with existing image coding standards.
UR - https://www.scopus.com/pages/publications/85020054599
U2 - 10.1109/DCC.2017.54
DO - 10.1109/DCC.2017.54
M3 - 会议稿件
AN - SCOPUS:85020054599
T3 - Data Compression Conference Proceedings
SP - 463
BT - Proceedings - DCC 2017, 2017 Data Compression Conference
A2 - Bilgin, Ali
A2 - Serra-Sagrista, Joan
A2 - Marcellin, Michael W.
A2 - Storer, James A.
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 Data Compression Conference, DCC 2017
Y2 - 4 April 2017 through 7 April 2017
ER -